© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 46083
    Prev
    Next
    INDEX
    Explanations

    after punctuation

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

    introduces examples or specific details

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     GI
    0.52
     OK
    0.50
    ك
    0.49
     or
    0.48
     peor
    0.47
     CVE
    0.47
     DAR
    0.46
     zehn
    0.46
    or
    0.46
     अनेक
    0.45
    POSITIVE LOGITS
    Anyways
    0.50
    Including
    0.48
     которой
    0.47
     incluyendo
    0.46
    <0xAC>
    0.46
    OneDrive
    0.46
    ependant
    0.45
    ADOS
    0.45
    Happiness
    0.45
    Therefore
    0.45
    Activations Density 0.037%

    No Known Activations