© 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. 30645
    Prev
    Next
    INDEX
    Explanations

    new means, most other, high speed

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

    AWS Spot Instances

    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
    де
    0.49
    on
    0.49
     to
    0.46
     on
    0.46
    य
    0.46
     workplace
    0.45
    ча
    0.43
     volg
    0.43
    лость
    0.43
     atro
    0.43
    POSITIVE LOGITS
     CLARK
    0.53
     कॉन्फ्रेंस
    0.49
     সেন্ট
    0.48
    协
    0.48
     እ
    0.47
     nguyên
    0.47
    之中
    0.47
    训练
    0.46
     MATHEMAT
    0.46
    决定
    0.46
    Activations Density 0.000%

    No Known Activations