© 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-262K
    7. 212371
    Prev
    Next
    INDEX
    Explanations

    language and data processing

    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
    athe
    0.46
    OT
    0.42
     sortie
    0.42
     Durchmesser
    0.42
    ifera
    0.41
    nameof
    0.40
    🌡
    0.39
    热
    0.39
    તના
    0.39
    utter
    0.38
    POSITIVE LOGITS
     cushions
    0.45
     installs
    0.44
     cards
    0.42
    Allows
    0.41
     Allows
    0.41
     crushes
    0.40
    欬
    0.39
     displays
    0.39
     engages
    0.38
    ஜ்
    0.38
    Activations Density 0.000%

    No Known Activations