© 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. 16-GEMMASCOPE-2-RES-262K
    4. 31778
    Prev
    Next
    INDEX
    Explanations

    by numbers

    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_16_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
     обла
    0.50
    </h3>
    0.49
     πολύ
    0.46
     décadas
    0.46
     одно
    0.44
    ;
    0.43
    </h2>
    0.42
    ️
    0.42
    ]),
    0.42
    ulated
    0.42
    POSITIVE LOGITS
    ುತ್ತೇನೆ
    0.56
    رسٹ
    0.54
    elsius
    0.51
    yaan
    0.51
    alaikumsalam
    0.50
    affaire
    0.49
    ंटी
    0.48
    ూర్
    0.47
    اونلو
    0.47
    گے
    0.46
    Activations Density 0.000%

    No Known Activations