© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 166467
    Prev
    Next
    INDEX
    Explanations

    private clients

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

    scented lotion

    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
    蝮
    0.45
    🩸
    0.45
    örn
    0.43
     التيار
    0.43
    եռ
    0.43
     poisons
    0.42
    Celltype
    0.42
     реки
    0.42
    ներ
    0.41
     клетки
    0.41
    POSITIVE LOGITS
    ниці
    0.53
     a
    0.46
    someone
    0.46
    genuine
    0.44
    issima
    0.44
    conce
    0.44
     responde
    0.44
     marques
    0.43
     realignment
    0.43
     ataupun
    0.43
    Activations Density 0.002%

    No Known Activations