© 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. 40-GEMMASCOPE-2-RES-262K
    7. 193561
    Prev
    Next
    INDEX
    Explanations

    Okay, responses

    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_40_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
    ូង
    0.44
     फर्नीचर
    0.41
    дите
    0.40
    ਿਕ
    0.39
    activ
    0.39
    obbies
    0.39
     жесто
    0.38
    פ
    0.38
    finder
    0.38
     بیک
    0.37
    POSITIVE LOGITS
     Reservation
    0.39
     SOC
    0.39
     six
    0.39
     rope
    0.38
     szervez
    0.38
     Intra
    0.37
     Świę
    0.37
     Gregorian
    0.37
     Six
    0.37
     Celsius
    0.37
    Activations Density 0.001%

    No Known Activations