© 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. 193620
    Prev
    Next
    INDEX
    Explanations

    hiring consult working

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

    lower precision / certain transactions

    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
    اتها
    0.52
    வையில்
    0.52
    thorace
    0.46
    विक
    0.46
     ход
    0.46
    >≥</
    0.46
     دائما
    0.45
     রাজশাহী
    0.44
     ইতোমধ্যে
    0.44
    த்துள்
    0.44
    POSITIVE LOGITS
    笵
    0.52
     erat
    0.50
     hilft
    0.42
     varie
    0.42
    leges
    0.42
     bude
    0.41
     amounted
    0.40
    aban
    0.40
     budou
    0.40
     zwięks
    0.40
    Activations Density 0.000%

    No Known Activations