© 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. 46507
    Prev
    Next
    INDEX
    Explanations

    method, action, or state

    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
    e
    0.43
     Russia
    0.43
     ().
    0.42
    J
    0.41
    sure
    0.41
     Coal
    0.41
     ftp
    0.41
     October
    0.40
     Investment
    0.40
     Мо
    0.40
    POSITIVE LOGITS
    נן
    0.48
    (!$
    0.46
    reira
    0.46
    远远
    0.46
    ithub
    0.45
     कौशिक
    0.44
     கலங்கரை
    0.43
     médic
    0.42
    尤其是
    0.42
     упаков
    0.42
    Activations Density 0.008%

    No Known Activations