© 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. 29397
    Prev
    Next
    INDEX
    Explanations

    publisher or book part

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

    book descriptions and course materials

    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
     পর্যালোচনা
    0.46
     Productions
    0.44
     Championships
    0.42
    :')
    0.42
    +".
    0.40
     সম্ভবনা
    0.40
     Çalış
    0.39
    最強
    0.39
     വ്യത്യസ്ത
    0.39
    之旅
    0.39
    POSITIVE LOGITS
     circulation
    0.41
     indors
    0.41
     impression
    0.40
    ब
    0.39
    <unused2017>
    0.39
    рім
    0.38
     conc
    0.38
     midday
    0.38
    ਬ
    0.38
    ब्बे
    0.38
    Activations Density 0.000%

    No Known Activations