© 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. 216581
    Prev
    Next
    INDEX
    Explanations

    harp seal, priority switch

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

    depends on

    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
    </b>
    0.52
     Organize
    0.50
    </strong>
    0.50
    </h2>
    0.47
    sa
    0.46
     investir
    0.43
    Position
    0.42
     প্রকৃতি
    0.40
    yrs
    0.40
     தெளி
    0.40
    POSITIVE LOGITS
    يدات
    0.50
    вал
    0.46
     consequat
    0.46
    乆
    0.46
     veľ
    0.46
     roche
    0.45
     než
    0.45
     făcut
    0.45
    וד
    0.45
     großen
    0.44
    Activations Density 0.000%

    No Known Activations