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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 49698
    Prev
    Next
    INDEX
    Explanations

    crows, birds, intelligence

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

    names and terminology related to bird species.

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

    The neuron fires on mentions of bird species (names or calls).

    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
     Ducks
    -0.84
    lielmo
    -0.81
    chium
    -0.81
     stroking
    -0.81
    ífer
    -0.81
    ודש
    -0.80
     TK
    -0.79
    IRED
    -0.78
    τογραφ
    -0.76
    Spice
    -0.76
    POSITIVE LOGITS
     crows
    1.03
     Crows
    1.02
     crow
    0.98
     ravens
    0.84
     intelligent
    0.80
    peanut
    0.80
    intelligent
    0.79
     intelligence
    0.75
     Crow
    0.73
    Rav
    0.72
    Activations Density 0.020%

    No Known Activations