© 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. 219528
    Prev
    Next
    INDEX
    Explanations

    Hubbard OR

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

    documentation format and technical explanations

    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
     ক্ষু
    0.49
     ໜ
    0.48
    <unused36>
    0.48
    venidas
    0.48
    anyahu
    0.47
     Иль
    0.47
    bi
    0.47
    <unused1103>
    0.47
     গবে
    0.46
     じゃん
    0.45
    POSITIVE LOGITS
    Rate
    0.62
    2
    0.56
    Plan
    0.53
    N
    0.51
    वरी
    0.51
    Sub
    0.49
    Answer
    0.49
    Dis
    0.49
    าม
    0.47
    Dou
    0.47
    Activations Density 0.000%

    No Known Activations