© 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. 98570
    Prev
    Next
    INDEX
    Explanations

    silver alloy

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

    awareness and strategy proposals

    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
    room
    0.47
    Watercolor
    0.46
    at
    0.43
    eem
    0.43
     paints
    0.42
     น้ํา
    0.42
    ab
    0.41
    t
    0.41
    thorne
    0.41
     watercolour
    0.41
    POSITIVE LOGITS
    ക്ട
    0.49
     háb
    0.49
    뱅
    0.48
     inmediato
    0.48
    ໕
    0.47
    ஊ
    0.47
    псо
    0.47
     Đối
    0.46
    腓
    0.46
     Ancak
    0.46
    Activations Density 0.000%

    No Known Activations