© 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. 74340
    Prev
    Next
    INDEX
    Explanations

    product, producer, or professor

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

    PostgreSQL query

    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
    Entre
    0.61
    Poland
    0.57
    M
    0.54
    B
    0.54
    ER
    0.53
    Australia
    0.52
    ouest
    0.52
    Մ
    0.52
    Bien
    0.51
    \<
    0.51
    POSITIVE LOGITS
    циями
    0.49
     spaz
    0.46
     vig
    0.43
     Rück
    0.42
     USB
    0.42
     Disc
    0.42
     NX
    0.41
     kling
    0.41
     иллюстрация
    0.41
    spolit
    0.41
    Activations Density 0.002%

    No Known Activations