© 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. 106676
    Prev
    Next
    INDEX
    Explanations

    measurement, suction holder, Tales of

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

    contrapositive

    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
    ز
    0.52
    ب
    0.42
    cas
    0.41
    naz
    0.41
    اط
    0.40
     spir
    0.40
    اين
    0.40
     construct
    0.40
    و
    0.39
    cycles
    0.39
    POSITIVE LOGITS
     পোশাক
    0.51
     audiobook
    0.51
     鞋
    0.50
     다르
    0.50
     seasoning
    0.50
     CORPER
    0.49
     フラワー
    0.49
    手册
    0.48
     ปก
    0.47
    ειτουργ
    0.47
    Activations Density 0.000%

    No Known Activations