© 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. 30180
    Prev
    Next
    INDEX
    Explanations

    coding, app, work, construction

    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
    มาะ
    0.46
    ດ້
    0.46
    کیل
    0.43
    тим
    0.43
    AsyncKeyState
    0.43
    ován
    0.42
     особенностей
    0.42
     ກ
    0.42
    மக்கு
    0.42
     WINTER
    0.42
    POSITIVE LOGITS
     و
    0.41
    未必
    0.39
     excision
    0.39
     مدينة
    0.38
    usually
    0.38
    intentional
    0.38
     हैरान
    0.37
    andaag
    0.37
     ಮತ್ತು
    0.36
    famous
    0.36
    Activations Density 0.004%

    No Known Activations