© 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. 7959
    Prev
    Next
    INDEX
    Explanations

    mannitol infusions

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

    avoidselective foreign terms

    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
    :
    0.54
     Adams
    0.53
     de
    0.52
     Things
    0.50
     Beers
    0.50
     Green
    0.50
     Sense
    0.48
     Seismic
    0.48
     LPC
    0.48
     menc
    0.47
    POSITIVE LOGITS
     ferrugineux
    0.54
    ایید
    0.53
    ബന്ധ
    0.52
    ⟣
    0.52
     rufo
    0.52
    恥
    0.50
    솎
    0.50
    会社
    0.50
    엷
    0.50
    ಲೆಯ
    0.50
    Activations Density 0.000%

    No Known Activations