© 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. 4067
    Prev
    Next
    INDEX
    Explanations

    gorilla or ape followed by specific words

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

    The neuron is detecting mentions of animal names (e.g. gorilla, Kong, ape, giraffe).

    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
    ähren
    -0.78
    繚
    -0.71
     busted
    -0.70
     Peep
    -0.70
    ZIP
    -0.69
     Hours
    -0.69
     Barns
    -0.69
     intolerance
    -0.69
     Helene
    -0.68
     Whip
    -0.68
    POSITIVE LOGITS
     gorilla
    2.42
     Gorilla
    2.05
    Gorilla
    1.74
    gorilla
    1.73
    🦍
    1.44
     gor
    1.41
     Gor
    1.41
    Gor
    1.35
    ゴリ
    1.26
     silver
    1.17
    Activations Density 0.016%

    No Known Activations