© 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. 86371
    Prev
    Next
    INDEX
    Explanations

    several weeks

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

    artistry, sword, originality, epic sagas

    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
    VING
    0.52
    ਰੇ
    0.45
     ripped
    0.44
    പടി
    0.44
    SKIP
    0.44
     abusing
    0.43
    }[(
    0.42
    <
    0.42
    azada
    0.41
    \{-
    0.41
    POSITIVE LOGITS
     NHT
    0.44
     персо
    0.42
    content
    0.42
     Blogger
    0.41
     vicenda
    0.41
     сим
    0.41
     cim
    0.40
     ка
    0.40
    Ohio
    0.40
     gênero
    0.40
    Activations Density 0.000%

    No Known Activations