© 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. 181604
    Prev
    Next
    INDEX
    Explanations

    information and its consequences

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

    ** or became

    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
     (
    0.45
    funciones
    0.44
     siehe
    0.44
    mouseout
    0.43
     tại
    0.41
     aquí
    0.40
     açık
    0.40
     codice
    0.39
    lardan
    0.39
     guzt
    0.39
    POSITIVE LOGITS
    度が
    0.46
    AppName
    0.46
     便利
    0.46
    捍
    0.46
    覓
    0.45
    াইব
    0.45
    偉
    0.45
     অবলম্বন
    0.44
    任務
    0.44
    驍
    0.43
    Activations Density 0.001%

    No Known Activations