© 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. 73325
    Prev
    Next
    INDEX
    Explanations

    hosting, receiving, versioning, for the, menu, play, more likely, rules about, that they, gold

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

    future dates and luxury

    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
     verwendeten
    0.54
    QAry
    0.52
     CCSDT
    0.51
     мел
    0.51
    を用いた
    0.49
     ನಾಲ್
    0.49
    <unused669>
    0.49
     използва
    0.49
     செயற்ப
    0.49
    獰
    0.49
    POSITIVE LOGITS
    0
    0.54
     prestigio
    0.49
    qu
    0.48
    1
    0.48
    8
    0.48
    I
    0.47
     Pulp
    0.46
     Advertise
    0.45
     to
    0.43
     Dates
    0.43
    Activations Density 0.000%

    No Known Activations