© 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
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 165965
    Prev
    Next
    INDEX
    Explanations

    contrastive conjunctions

    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_40_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
    );
    0.59
    };
    0.47
    !);
    0.46
    )$;
    0.46
    ;
    0.45
    дон
    0.44
    }$;
    0.44
    %;
    0.43
    ).}
    0.43
    >;
    0.42
    POSITIVE LOGITS
     but
    0.56
     ancak
    0.50
     lakini
    0.49
     لكن
    0.47
     కానీ
    0.46
     ngunit
    0.45
     []
    0.45
     परन्तु
    0.45
    but
    0.44
     परंतु
    0.44
    Activations Density 0.002%

    No Known Activations