© 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. 132076
    Prev
    Next
    INDEX
    Explanations

    use will

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

    not in order

    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
    ισμού
    0.53
     Cómo
    0.50
    戯
    0.50
    當年
    0.49
    日閲覧
    0.46
     اعزائي
    0.46
     není
    0.46
    的用户
    0.46
    測定
    0.45
    قاف
    0.45
    POSITIVE LOGITS
    {
    0.50
    F
    0.49
    ه
    0.49
    All
    0.48
    R
    0.47
    Benefit
    0.46
    E
    0.46
    Enh
    0.46
    alto
    0.45
    L
    0.45
    Activations Density 0.000%

    No Known Activations