© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 161765
    Prev
    Next
    INDEX
    Explanations

    cornstarch and, resemble small, researching articles

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

    work quickly

    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
     बाकी
    0.44
    篇
    0.43
     পারে
    0.42
     unacceptable
    0.42
     vulnerable
    0.41
     familiar
    0.41
     Bereiche
    0.40
     su
    0.40
    ادل
    0.40
     orientado
    0.39
    POSITIVE LOGITS
    ეტ
    0.55
    拶
    0.54
    ᱔
    0.49
     dź
    0.47
    ਲ
    0.47
     velocità
    0.46
     bě
    0.46
     épars
    0.46
    heads
    0.46
     percor
    0.46
    Activations Density 0.000%

    No Known Activations