© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 37816
    Prev
    Next
    INDEX
    Explanations

    was like

    np_acts-logits-general · gemini-2.5-flash-lite

    reduced alertness, respiratory depression

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    限量
    0.44
    𝘐
    0.43
     textual
    0.43
    ಸ್ಟ್
    0.42
    Crop
    0.42
    etext
    0.42
    GetData
    0.41
    作物
    0.41
    ઃ
    0.41
     actores
    0.40
    POSITIVE LOGITS
     veya
    0.43
    也可以
    0.41
    زمان
    0.40
     homeowner
    0.39
     রাজনীতিবিদ
    0.38
     median
    0.38
    oncé
    0.38
     Owners
    0.38
     dent
    0.37
     Vicki
    0.37
    Activations Density 0.000%

    No Known Activations