© 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. 31-GEMMASCOPE-2-RES-65K
    7. 14914
    Prev
    Next
    INDEX
    Explanations

    new things every day

    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_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
     барои
    0.42
     некоторых
    0.42
    엎
    0.41
     Unfortunately
    0.40
     some
    0.40
     могло
    0.40
     however
    0.40
     coloro
    0.40
     parents
    0.40
     जरुरत
    0.39
    POSITIVE LOGITS
    ونية
    0.39
    قتص
    0.38
     코로나
    0.38
     ശ്രീ
    0.37
    <unused38>
    0.37
    covid
    0.37
    耻
    0.37
     DROP
    0.37
    ECONOMIC
    0.36
     vuoden
    0.36
    Activations Density 0.040%

    No Known Activations