© 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. 99177
    Prev
    Next
    INDEX
    Explanations

    history and details

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

    technical or descriptive terms

    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
     juice
    0.46
    [-
    0.44
    ++)
    0.42
     ju
    0.42
    ish
    0.42
    تور
    0.42
    ☘
    0.42
    (-
    0.41
     Sahara
    0.41
     chef
    0.39
    POSITIVE LOGITS
     Стар
    0.61
     विचारधारा
    0.54
     చరిత్ర
    0.54
     деталей
    0.52
     అయిన
    0.52
     отдела
    0.51
     हिस्ट्री
    0.50
     unwelcome
    0.50
    ENCIAS
    0.50
     கூட்டணிய
    0.50
    Activations Density 0.001%

    No Known Activations