© 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. 38008
    Prev
    Next
    INDEX
    Explanations

    item added to cart

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

    risks or harm

    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
    ↵
    0.46
    airport
    0.40
    USTOM
    0.40
    _
    0.40
     it
    0.39
    αλ
    0.39
    URO
    0.39
    URF
    0.39
     penetrate
    0.39
    produce
    0.39
    POSITIVE LOGITS
     عن
    0.45
     بالنسبة
    0.45
     პირადი
    0.45
    勇气
    0.44
     উপকরণ
    0.43
     سابق
    0.42
     لأ
    0.42
     sämt
    0.42
     وعد
    0.41
    瞩
    0.41
    Activations Density 0.000%

    No Known Activations