© 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. 91864
    Prev
    Next
    INDEX
    Explanations

    writer, solicitation

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

    The neuron fires on comic‐book issue citations—tokens like “#256 by Peter David and Leonard Kirk” that combine a hash‐number and a “by” author credit.

    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
    unga
    -0.83
    arov
    -0.70
    沿革
    -0.69
    tod
    -0.69
    
    -0.68
    PENDING
    -0.66
     prostagland
    -0.66
    แตก
    -0.66
    前から
    -0.66
    umfang
    -0.65
    POSITIVE LOGITS
     solicit
    0.92
    ivir
    0.85
     solic
    0.83
    oraf
    0.81
     solicitud
    0.81
     solicitation
    0.80
     writer
    0.79
    solic
    0.79
    Variants
    0.78
    VARIANT
    0.78
    Activations Density 0.039%

    No Known Activations