© 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. 48181
    Prev
    Next
    INDEX
    Explanations

    relevant courses

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

    broken down by category

    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
    手が
    0.48
     cơ
    0.48
     recevoir
    0.46
     ejecutar
    0.45
     bắt
    0.45
     eléctrico
    0.44
     exponer
    0.44
    ᒋ
    0.44
     CrL
    0.43
     recibir
    0.43
    POSITIVE LOGITS
     الحكوم
    0.53
    MV
    0.51
    KS
    0.51
    LIN
    0.50
    lineContainer
    0.49
    ger
    0.48
    يفي
    0.47
    NSE
    0.46
    stel
    0.46
    MU
    0.45
    Activations Density 0.000%

    No Known Activations