© 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. 177664
    Prev
    Next
    INDEX
    Explanations

    states of being

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

    universities, adults, EVs, mission

    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
    ור
    0.43
    и
    0.43
    and
    0.42
    а
    0.42
    or
    0.41
    ra
    0.41
    轻松
    0.41
    và
    0.40
    ר
    0.40
    Q
    0.39
    POSITIVE LOGITS
     süd
    0.45
     fum
    0.45
     deu
    0.44
     campagna
    0.44
     filmes
    0.44
     piel
    0.43
     zahl
    0.43
     mū
    0.43
     grunge
    0.43
     deco
    0.43
    Activations Density 0.002%

    No Known Activations