© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 162255
    Prev
    Next
    INDEX
    Explanations

    style and graphic descriptions

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

    breakdown, how, what

    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
    ‭
    0.49
    -
    0.49
    :
    0.49
     ranked
    0.48
    water
    0.47
     asked
    0.45
    _{
    0.44
     requested
    0.44
     aromat
    0.43
     played
    0.43
    POSITIVE LOGITS
    }\|_{
    0.59
     ತಾ
    0.56
    берриз
    0.55
     入っ
    0.55
    <unused1879>
    0.49
    sid
    0.48
     газе
    0.48
     निजात
    0.48
    𒁍
    0.47
     ನೆಲ
    0.47
    Activations Density 0.000%

    No Known Activations