© 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. 104511
    Prev
    Next
    INDEX
    Explanations

    fitting clothes, steep radii, searching

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

    measurement or quantity context

    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
    DAY
    0.50
    day
    0.49
     say
    0.48
     benefit
    0.48
    ↵↵
    0.48
     kep
    0.47
    say
    0.47
     buck
    0.46
    разу
    0.46
    benefit
    0.46
    POSITIVE LOGITS
     開始
    0.63
     头
    0.56
     入っ
    0.55
     書い
    0.54
     متجه
    0.53
     連
    0.51
     начну
    0.51
     那麼
    0.50
     غير
    0.50
     刺繍
    0.50
    Activations Density 0.000%

    No Known Activations