© 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. 61893
    Prev
    Next
    INDEX
    Explanations

    Almanya, ota,椅, કુટુંબા

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

    God Bless

    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
    veda
    0.54
    vec
    0.46
     وف
    0.44
    Jenn
    0.44
    鹽
    0.44
    FLO
    0.44
    obje
    0.44
    THROW
    0.44
    velo
    0.41
    鈦
    0.41
    POSITIVE LOGITS
     Almanya
    0.55
    ோட
    0.54
     椅
    0.54
     कुटुंबा
    0.52
     actifs
    0.52
    ს
    0.51
     ACTIV
    0.51
     Cumhur
    0.50
     Aralık
    0.50
     Baş
    0.49
    Activations Density 0.000%

    No Known Activations