© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 76882
    Prev
    Next
    INDEX
    Explanations

    Suri descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ethnic
    0.44
     effectually
    0.43
     issue
    0.42
    geq
    0.42
    );
    0.41
    za
    0.41
    łka
    0.41
    qt
    0.41
    leq
    0.40
    }}$;
    0.40
    POSITIVE LOGITS
    Buck
    0.50
     rejet
    0.48
     Log
    0.47
    Kann
    0.46
     Kann
    0.45
     Wolverine
    0.44
    ᴥ
    0.44
     защи
    0.44
     безопас
    0.44
     poli
    0.44
    Activations Density 0.001%

    No Known Activations