© 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. 3845
    Prev
    Next
    INDEX
    Explanations

    academic or professional contexts

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

    technical or specific terms

    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
     Gal
    0.36
     لو
    0.35
    </tr>
    0.34
     (
    0.34
    áva
    0.34
    ky
    0.33
    ando
    0.33
    ėje
    0.33
    <sup>
    0.32
     rope
    0.32
    POSITIVE LOGITS
    ਾਨੂੰ
    0.44
    蛲
    0.40
     peneliti
    0.40
    PipelineState
    0.40
    第一題
    0.40
     паци
    0.39
    銠
    0.39
    Prototype
    0.38
    題目
    0.38
    Pada
    0.37
    Activations Density 0.000%

    No Known Activations