© 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. 173317
    Prev
    Next
    INDEX
    Explanations

    wondered how

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

    prompt and cultures

    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
     ಆಹಾರ
    0.46
     caballos
    0.46
     huyết
    0.45
    ሖ
    0.44
     identidade
    0.44
    ᱖
    0.44
    ରି
    0.44
    тый
    0.43
     finalText
    0.42
     numele
    0.42
    POSITIVE LOGITS
    Busy
    0.45
    在我们
    0.45
     focussed
    0.44
    0.44
    /
    0.43
    Clip
    0.43
    Scale
    0.42
     Lazada
    0.42
    Plus
    0.42
     GDPR
    0.42
    Activations Density 0.002%

    No Known Activations