© 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. 121374
    Prev
    Next
    INDEX
    Explanations

    email, substitutions, assistance, spheres, N, Yes

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

    discussing safety, harm, or modification

    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
    <unused61>
    0.55
    ío
    0.47
    0.46
     加
    0.46
    <unused63>
    0.46
    0.45
    islava
    0.45
     RMB
    0.44
    illae
    0.44
    illier
    0.44
    POSITIVE LOGITS
     الشيطان
    0.46
    볶
    0.46
    褻
    0.45
    职业
    0.44
     영화
    0.44
    痱
    0.44
    忏
    0.43
    毗
    0.43
     آزادی
    0.43
    餾
    0.43
    Activations Density 0.001%

    No Known Activations