© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 972
    Prev
    Next
    INDEX
    Explanations

    range( function calls

    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
     abandoning
    0.43
    ␮
    0.43
    তই
    0.40
    \{-
    0.40
     slaw
    0.39
     diminue
    0.39
     tumble
    0.38
     AVER
    0.38
     thinner
    0.38
     cori
    0.38
    POSITIVE LOGITS
    urban
    0.46
    rung
    0.42
    map
    0.41
    under
    0.39
    oglob
    0.39
     செயல்படுத்த
    0.39
    music
    0.39
     NLG
    0.39
    증
    0.39
    Urban
    0.38
    Activations Density 0.014%

    No Known Activations