© 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. 130874
    Prev
    Next
    INDEX
    Explanations

    future

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

    technical terms and programming

    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
     lilac
    0.48
     imper
    0.48
    ।
    0.48
     otom
    0.46
    まずは
    0.46
     aquare
    0.44
     penultimate
    0.44
     Levant
    0.43
     '*',
    0.43
    𝓭
    0.43
    POSITIVE LOGITS
     hábito
    0.50
    తీ
    0.49
    นิด
    0.48
    (
    0.46
    উদাহরণ
    0.45
    ре
    0.44
    चीन
    0.44
    রোধ
    0.43
    विला
    0.43
    তুম
    0.43
    Activations Density 0.000%

    No Known Activations