© 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. 74753
    Prev
    Next
    INDEX
    Explanations

    charity evaluator GiveWell

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

    building a tower

    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
    afin
    0.45
     ブリ
    0.44
    äne
    0.43
     Sulph
    0.41
     ime
    0.40
     crainte
    0.40
     emanating
    0.40
    饪
    0.40
    ansom
    0.39
     ইঙ্গ
    0.39
    POSITIVE LOGITS
    lies
    0.48
    Families
    0.48
    Conditional
    0.45
     табли
    0.44
    calculations
    0.44
    prestations
    0.43
     треба
    0.43
     WILD
    0.43
    uerdo
    0.42
     дня
    0.42
    Activations Density 0.003%

    No Known Activations