© 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. 153550
    Prev
    Next
    INDEX
    Explanations

    precise printing or island names

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

    revocation

    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
    lini
    0.44
     repressive
    0.43
    喑
    0.43
    ✻
    0.42
    כ
    0.42
    煕
    0.42
     которым
    0.41
    LECTION
    0.41
     Practically
    0.41
     '.</
    0.40
    POSITIVE LOGITS
    Client
    0.46
    ضيف
    0.45
    多次
    0.43
     pią
    0.42
     cinco
    0.42
     Client
    0.41
     Transformers
    0.41
     nitrog
    0.41
     cinq
    0.40
     spat
    0.40
    Activations Density 0.001%

    No Known Activations