© 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. 25282
    Prev
    Next
    INDEX
    Explanations

    simple leveled reading materials

    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
    きたいと思います
    0.50
    LocalStorage
    0.42
    курс
    0.40
     secretaria
    0.39
     व्यक्तित्व
    0.39
     conversación
    0.38
    客服
    0.38
    💅
    0.38
    斦
    0.38
     কোর্স
    0.38
    POSITIVE LOGITS
     low
    0.44
     leveled
    0.43
     text
    0.43
     livello
    0.43
    涡
    0.42
     reduced
    0.42
     Low
    0.41
     低
    0.41
     favore
    0.40
    ichloro
    0.40
    Activations Density 0.057%

    No Known Activations