© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 110649
    Prev
    Next
    INDEX
    Explanations

    missionaries, tourists, failure

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

    personal growth

    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
     weighted
    0.48
    कालय
    0.47
    ']}
    0.46
    عهد
    0.46
     쓰
    0.46
     runny
    0.46
     substitutional
    0.45
     قيمه
    0.45
     saddo
    0.45
     situated
    0.44
    POSITIVE LOGITS
    agu
    0.53
    nets
    0.50
     Nets
    0.50
    和小
    0.49
    linde
    0.48
     blanche
    0.48
     Access
    0.47
    tong
    0.46
    gut
    0.46
    翘
    0.46
    Activations Density 0.001%

    No Known Activations