© 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-IT
    5. 16-GEMMASCOPE-2-RES-65K
    7. 2861
    Prev
    Next
    INDEX
    Explanations

    section headings or introductions

    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_65k_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
    ");
    1.09
     حسين
    1.05
    ため
    1.02
    는데
    1.02
    ];
    1.01
    ול
    0.99
     Reihe
    0.99
    を持ち
    0.99
     hrane
    0.98
    اني
    0.98
    POSITIVE LOGITS
    ب
    1.70
    ه
    1.61
    u
    1.51
    ص
    1.51
    in
    1.48
    ो
    1.48
    ו
    1.45
    و
    1.45
    i
    1.41
    ف
    1.38
    Activations Density 0.016%

    No Known Activations