© 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. 2065
    Prev
    Next
    INDEX
    Explanations

    introduces an alternative

    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
    ;
    0.91
    _
    0.90
    ה
    0.83
     ו
    0.82
     були
    0.80
    นาย
    0.79
     accessori
    0.77
    inafter
    0.75
    น้อง
    0.74
     are
    0.73
    POSITIVE LOGITS
    л
    1.34
    s
    1.33
    ना
    1.20
    ل
    1.09
    ش
    0.96
    to
    0.95
    ग
    0.94
    uk
    0.93
    ્રી
    0.92
    т
    0.90
    Activations Density 0.513%

    No Known Activations