© 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. 202597
    Prev
    Next
    INDEX
    Explanations

    listing details after introductory phrases

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

    These things and information

    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
     אף
    0.43
     jde
    0.43
     রেফার
    0.43
     форум
    0.42
    覧
    0.42
    お問い合わせ
    0.42
    স্ক
    0.42
    邦
    0.41
    加速度
    0.41
    明確
    0.40
    POSITIVE LOGITS
     hải
    0.47
     সঞ্জীবনী
    0.46
    kN
    0.46
    kar
    0.46
    học
    0.46
    ém
    0.45
    sproz
    0.45
    ((\
    0.45
     ngọt
    0.45
    seeds
    0.44
    Activations Density 0.001%

    No Known Activations