© 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. 212821
    Prev
    Next
    INDEX
    Explanations

    personal use

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

    health and work aspects

    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
     लष्
    0.47
    🥺
    0.46
    🤪
    0.46
    బ్ద
    0.45
    柰
    0.45
    部件
    0.43
    䀓
    0.43
    锜
    0.42
     bohemian
    0.42
    আয়
    0.42
    POSITIVE LOGITS
     elapse
    0.48
    hous
    0.48
     ONLY
    0.46
    free
    0.44
     TV
    0.43
    anyl
    0.42
    luit
    0.42
    black
    0.42
    elapsed
    0.41
     odstr
    0.41
    Activations Density 0.002%

    No Known Activations