© 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-65K
    7. 55220
    Prev
    Next
    INDEX
    Explanations

    deviation from the norm

    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_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
    Vall
    0.43
     Vall
    0.42
     Input
    0.42
     Imp
    0.40
     gefähr
    0.40
     переме
    0.39
     acheté
    0.39
    in
    0.39
     vall
    0.39
    POSITIVE LOGITS
     '(
    0.46
     "(
    0.44
    textit
    0.44
     "$
    0.42
     "'
    0.41
    curity
    0.40
     newsp
    0.39
     ዋና
    0.39
     “‘
    0.38
     оригинала
    0.38
    Activations Density 0.007%

    No Known Activations