© 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. 51695
    Prev
    Next
    INDEX
    Explanations

    importing code libraries

    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
    0.44
    eppo
    0.39
     Jazeera
    0.36
    eqnarray
    0.36
    phrase
    0.36
     fred
    0.36
    繰り返
    0.35
    確認
    0.35
    ৬
    0.35
    임을
    0.35
    POSITIVE LOGITS
     படங்கள்
    0.45
     allemand
    0.44
    jahteraan
    0.44
     substitutes
    0.43
     ücret
    0.43
     étrangers
    0.43
    Mas
    0.42
    Tan
    0.42
     estética
    0.42
     comercial
    0.41
    Activations Density 0.006%

    No Known Activations