© 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. 48936
    Prev
    Next
    INDEX
    Explanations

    INTEGER VARIABLE

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

    content creation and writing

    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
    𝙏
    0.46
     أد
    0.44
    𝙡
    0.43
     thở
    0.42
    ண
    0.42
     suited
    0.42
     calcS
    0.42
     gql
    0.42
     económ
    0.41
    难以
    0.41
    POSITIVE LOGITS
    h
    0.53
    sp
    0.52
     താര
    0.52
    night
    0.50
     between
    0.49
    f
    0.49
    ss
    0.48
    sh
    0.47
     квартира
    0.47
     ONU
    0.47
    Activations Density 0.000%

    No Known Activations