© 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. 83678
    Prev
    Next
    INDEX
    Explanations

    technical documentation and specific terms

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

    physics user applications

    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
    테
    0.57
    Га
    0.47
    Ге
    0.46
    دیای
    0.44
    Estas
    0.44
     illust
    0.44
    िद
    0.44
    тивов
    0.44
    彆
    0.44
    เผ
    0.43
    POSITIVE LOGITS
     WP
    0.48
     NICE
    0.46
     NPR
    0.45
     MS
    0.45
     NRS
    0.45
     pierwszym
    0.45
     conoc
    0.44
     RS
    0.44
     TSR
    0.44
     do
    0.44
    Activations Density 0.000%

    No Known Activations