© 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. 90392
    Prev
    Next
    INDEX
    Explanations

    technical terms and following words

    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
     Ruhe
    0.42
     Milestone
    0.41
     showbiz
    0.40
     tante
    0.40
     \
    0.39
     Other
    0.39
     เล่น
    0.39
     multitude
    0.39
     newbies
    0.39
     newbie
    0.39
    POSITIVE LOGITS
    reflectionCamera
    0.46
    पहरण
    0.46
    锹
    0.43
    Yaml
    0.43
     infringer
    0.43
     upravo
    0.42
     оцени
    0.41
     drawRight
    0.41
    TxtArea
    0.41
    ）【
    0.41
    Activations Density 0.003%

    No Known Activations