© 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. 122872
    Prev
    Next
    INDEX
    Explanations

    encouraging and calling people

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

    historical ambiguity and difficulty

    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
     equivalence
    0.44
     其他
    0.44
     ค่า
    0.43
    陬
    0.43
     یق
    0.43
    擰
    0.42
    パナソニック
    0.42
    其他的
    0.41
    阁
    0.41
    桕
    0.41
    POSITIVE LOGITS
     thờ
    0.55
    bildungs
    0.52
    städ
    0.50
    dach
    0.49
     históricos
    0.48
     wee
    0.48
    resting
    0.48
    buildings
    0.46
    lEdit
    0.46
    ಳ್
    0.46
    Activations Density 0.001%

    No Known Activations