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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 139297
    Prev
    Next
    INDEX
    Explanations

    states and graphs

    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
    नंतर
    0.49
     sectoral
    0.46
    신도시
    0.46
     continuando
    0.46
    طة
    0.43
     insistent
    0.43
    椽
    0.42
     creando
    0.40
     площад
    0.40
    යෙන්
    0.40
    POSITIVE LOGITS
    on
    0.47
    いますが
    0.47
    ๕
    0.46
    pict
    0.46
    f
    0.46
    ៥
    0.44
     spn
    0.44
     ಒಬ್ಬ
    0.42
     Оно
    0.42
    améli
    0.42
    Activations Density 0.005%

    No Known Activations