© 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. 227518
    Prev
    Next
    INDEX
    Explanations

    semantic content identification

    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
     пише
    0.48
     сфе
    0.48
     Políticas
    0.47
     Podcasts
    0.47
     ఆడ
    0.47
     русского
    0.46
     with
    0.46
    ᄊ
    0.46
     ఏడాది
    0.46
     Ау
    0.46
    POSITIVE LOGITS
     redemption
    0.47
     salvation
    0.45
    ouncil
    0.44
    UNCIL
    0.44
    SAP
    0.43
    JS
    0.42
    StripMenuItem
    0.42
     contemplation
    0.42
    Chip
    0.42
     deliverance
    0.41
    Activations Density 0.001%

    No Known Activations