© 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-262K
    7. 47426
    Prev
    Next
    INDEX
    Explanations

    chronic, enum, cabin, beyond

    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
     Ar
    0.54
     Re
    0.51
     Automation
    0.50
     Mig
    0.48
    a
    0.48
     It
    0.48
     I
    0.45
    Ar
    0.45
     Gra
    0.45
     Per
    0.44
    POSITIVE LOGITS
     ጥሩ
    0.50
     мало
    0.49
     литератур
    0.49
     novelists
    0.48
     thẻ
    0.48
     getClass
    0.46
     детям
    0.46
     שנה
    0.46
    czki
    0.46
     событий
    0.46
    Activations Density 0.000%

    No Known Activations