© 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. 83136
    Prev
    Next
    INDEX
    Explanations

    ideas combined

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

    concepts and evaluations

    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
     感
    0.46
    劫
    0.46
     করতাম
    0.44
     Hölder
    0.44
    ച്
    0.42
    离开了
    0.42
    魅
    0.41
     HOLD
    0.41
     নজরুল
    0.40
    ارج
    0.40
    POSITIVE LOGITS
     ದೇಶ
    0.46
    และ
    0.46
    คะ
    0.45
     sexo
    0.44
    ță
    0.43
    tenant
    0.43
    är
    0.43
    таки
    0.43
    tariff
    0.42
    ţ
    0.42
    Activations Density 0.000%

    No Known Activations