© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 100266
    Prev
    Next
    INDEX
    Explanations

    Parasite North Island

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     આરો
    0.50
    ᱡ
    0.47
     historias
    0.47
    яна
    0.46
     famílias
    0.46
     familias
    0.45
    vegetarian
    0.45
     mitologia
    0.45
    aut
    0.44
     каран
    0.43
    POSITIVE LOGITS
     WALTER
    0.42
     prest
    0.42
    בי
    0.41
    ⿴
    0.40
    queous
    0.40
    ក្នុង
    0.39
     Readiness
    0.39
     winds
    0.38
    ל
    0.38
    ง่าย
    0.37
    Activations Density 0.000%

    No Known Activations