© 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. 161751
    Prev
    Next
    INDEX
    Explanations

    beauty is

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

    chemicals, gases, and intelligence

    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
     télécharg
    0.52
     anglais
    0.50
    ۷
    0.50
    "،
    0.50
     Віль
    0.50
    น์
    0.49
     Фі
    0.48
    ㅀ
    0.48
    ր
    0.48
    ៧
    0.48
    POSITIVE LOGITS
     nM
    0.52
     mixts
    0.47
     differentiable
    0.47
     reagents
    0.46
    TZ
    0.46
    pairs
    0.44
    ேச
    0.44
    inetics
    0.44
     moieties
    0.44
     NG
    0.43
    Activations Density 0.001%

    No Known Activations