© 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. 10858
    Prev
    Next
    INDEX
    Explanations

    challenging, offering, gradient, raum, remainder

    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
    </h2>
    0.52
    bah
    0.49
    후
    0.48
    ה
    0.48
    Bah
    0.48
    </h3>
    0.48
    </h4>
    0.47
    >
    0.47
    зо
    0.47
    ↵
    0.47
    POSITIVE LOGITS
    嘬
    0.51
    睞
    0.49
     Ninth
    0.46
    緘
    0.45
     ablation
    0.44
     ขวด
    0.43
    吶
    0.43
     ninth
    0.43
    okhlov
    0.43
    শকা
    0.43
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.