© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 50125
    Prev
    Next
    INDEX
    Explanations

    flexibility and functionality

    np_acts-logits-general · gemini-2.5-flash-lite

    differences and variations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ניה
    0.56
    ری
    0.50
    ט
    0.48
     ludicrous
    0.48
     Потому
    0.47
    ười
    0.47
    так
    0.46
     क्रोध
    0.46
     Aufgrund
    0.46
    בו
    0.45
    POSITIVE LOGITS
     differences
    0.46
     flexibility
    0.44
    差異
    0.43
     disseminated
    0.42
    鱗
    0.42
     JAMA
    0.41
     свободно
    0.41
     изменений
    0.41
     PARTS
    0.40
     diferentes
    0.40
    Activations Density 0.000%

    No Known Activations