© 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. 14348
    Prev
    Next
    INDEX
    Explanations

    appeared first on

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

    tailor to specific needs

    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
    });
    0.42
    点は
    0.39
    ;
    0.38
     αυτές
    0.38
     Alic
    0.37
    வையை
    0.37
    <0xE3>
    0.37
    陖
    0.37
     salen
    0.37
     anal
    0.37
    POSITIVE LOGITS
     Новости
    0.51
     .”
    0.46
    .“
    0.44
     ».
    0.42
    Blog
    0.42
    Publications
    0.41
    .»
    0.41
    Journal
    0.41
    ব্লিউ
    0.41
     பிரி
    0.40
    Activations Density 0.002%

    No Known Activations