© 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. 107131
    Prev
    Next
    INDEX
    Explanations

    reserve or change

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

    neutralize or rated tubing

    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
     দুঃ
    0.52
    ﺶ
    0.47
    ภัย
    0.47
     ফুলের
    0.46
    หนด
    0.44
    ').':
    0.44
     কিছু
    0.43
     []:
    0.43
     cuentan
    0.43
    เร็จ
    0.43
    POSITIVE LOGITS
     neutrals
    0.55
     neutralize
    0.55
     ครับ
    0.49
     neutralized
    0.46
     divina
    0.46
    таки
    0.45
    neutral
    0.45
     novos
    0.44
    tiin
    0.44
    EDES
    0.44
    Activations Density 0.001%

    No Known Activations