© 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. 20640
    Prev
    Next
    INDEX
    Explanations

    Crash

    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
    憸
    0.47
     klare
    0.46
     étoiles
    0.44
     elementów
    0.44
     affiliations
    0.43
     Jair
    0.43
     والے
    0.42
     griev
    0.42
     afge
    0.41
    tweets
    0.41
    POSITIVE LOGITS
    生意
    0.50
     Rp
    0.48
    逐
    0.46
     SQL
    0.43
     ₽
    0.42
     SME
    0.41
    PPT
    0.41
    igual
    0.41
     Pp
    0.40
     bitmaps
    0.39
    Activations Density 0.006%

    No Known Activations