© 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. 248765
    Prev
    Next
    INDEX
    Explanations

    context completion

    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
    ﮔ
    0.54
     پہا
    0.47
    پل
    0.46
     Studium
    0.45
    ဋ
    0.45
     alleviating
    0.44
    کرا
    0.44
     フレーム
    0.44
    נג
    0.44
    டத்தில்
    0.43
    POSITIVE LOGITS
    Я
    0.52
    相信
    0.50
    /
    0.48
    <h4>
    0.48
    大家好
    0.48
    ],
    0.46
     drawSprites
    0.46
    О
    0.45
    大家都
    0.44
     drawRight
    0.44
    Activations Density 0.000%

    No Known Activations