© 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. 161260
    Prev
    Next
    INDEX
    Explanations

    holidays and events

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

    compression efficiency

    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
     capitán
    0.49
    imil
    0.45
    iré
    0.44
     של
    0.43
     Joss
    0.42
     también
    0.41
     chua
    0.41
     {{{
    0.41
     José
    0.40
     go
    0.40
    POSITIVE LOGITS
     tủ
    0.49
     electrop
    0.48
     обстанов
    0.48
    Ყ
    0.47
     espect
    0.46
     письмен
    0.46
     stwier
    0.46
    hadap
    0.45
    󠁴
    0.45
    веден
    0.45
    Activations Density 0.000%

    No Known Activations