© 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. 46741
    Prev
    Next
    INDEX
    Explanations

    victim card or surviving life

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

    list items being specified

    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
    t
    0.65
    R
    0.54
    j
    0.52
    add
    0.50
    a
    0.50
    CO
    0.47
    l
    0.46
    et
    0.46
    5
    0.46
    高度
    0.46
    POSITIVE LOGITS
    ꫝ
    0.50
    ⇰
    0.50
     방법에
    0.49
    纮
    0.48
     پایان
    0.46
     Jamal
    0.46
     glaring
    0.45
     foodstuffs
    0.45
    ılar
    0.45
     경우에는
    0.45
    Activations Density 0.000%

    No Known Activations