© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 65409
    Prev
    Next
    INDEX
    Explanations

    sardines and herring

    np_acts-logits-general · gemini-2.5-flash-lite

    This neuron identifies species of small fish, particularly sardines, anchovies, and herring.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The main thing this neuron does is detect mentions of fish species by name.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    foo
    -0.74
    isateur
    -0.74
     Praha
    -0.73
    пра
    -0.73
     biri
    -0.72
    ρει
    -0.70
    龟
    -0.70
     הא
    -0.70
     Poder
    -0.70
     root
    -0.70
    POSITIVE LOGITS
     sardines
    1.54
    sard
    1.45
     sard
    1.45
     ancho
    1.37
    Ancho
    1.27
     Ancho
    1.21
     Sard
    1.16
    ancho
    1.02
     canned
    0.98
     herring
    0.91
    Activations Density 0.029%

    No Known Activations