© 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. 111932
    Prev
    Next
    INDEX
    Explanations

    attribution after speech

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

    description of next steps

    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
    assembling
    0.46
    ందుకు
    0.46
     atuais
    0.43
     actuales
    0.43
    Instructions
    0.41
    🄰
    0.41
     कमीशन
    0.40
    飨
    0.40
     quarterly
    0.40
     খরচ
    0.40
    POSITIVE LOGITS
     加
    0.46
     TInner
    0.44
     但是
    0.42
     काट
    0.42
     太
    0.41
     resistive
    0.40
     。
    0.38
     BB
    0.38
    ")}}'
    0.38
     Pengh
    0.38
    Activations Density 0.004%

    No Known Activations