© 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. 66451
    Prev
    Next
    INDEX
    Explanations

    raised from, post on, Saturday at

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

    gift ideas using specific categories

    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
    <0x0D>
    0.48
     plage
    0.44
    <0xEF>
    0.42
     predominate
    0.42
    ﻧ
    0.41
    1
    0.41
    ‥
    0.41
     حمله
    0.40
    ad
    0.40
     courant
    0.40
    POSITIVE LOGITS
    osch
    0.48
     Journals
    0.47
     erle
    0.46
    忥
    0.45
     dritte
    0.45
    osw
    0.45
     Thirdly
    0.44
     teilweise
    0.44
     जॉ
    0.43
    itôt
    0.42
    Activations Density 0.000%

    No Known Activations