© 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. 34577
    Prev
    Next
    INDEX
    Explanations

    player apparently

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

    not X but Y

    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
     overw
    0.49
    </code>
    0.45
     I
    0.42
     ±
    0.42
     end
    0.41
     枚
    0.41
     TTL
    0.41
     support
    0.40
     maximum
    0.40
     coi
    0.40
    POSITIVE LOGITS
    nang
    0.49
    𒊑
    0.46
    aths
    0.44
    notlocked
    0.43
     তাড়
    0.42
    धिकारिक
    0.41
    मिताभ
    0.41
    ম্মদ
    0.41
    არ
    0.41
     এড়িয়ে
    0.41
    Activations Density 0.000%

    No Known Activations