© 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. 99191
    Prev
    Next
    INDEX
    Explanations

    buying bot functionality

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

    program completion

    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
     triun
    0.50
    neighbour
    0.49
    strength
    0.45
    🇽
    0.44
    tenth
    0.43
    ریض
    0.43
     entram
    0.42
    τρα
    0.42
    Neigh
    0.42
    ología
    0.41
    POSITIVE LOGITS
    ูนย์
    0.47
     Aide
    0.47
     Aiken
    0.46
    ヤモンド
    0.45
    óság
    0.44
     பிரதி
    0.44
    味的
    0.43
    dagen
    0.43
    掾
    0.43
    委員
    0.43
    Activations Density 0.001%

    No Known Activations