© 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. 40-GEMMASCOPE-2-RES-262K
    7. 224390
    Prev
    Next
    INDEX
    Explanations

    value, store, changes

    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_40_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
     behaves
    0.40
     ă
    0.40
    인다
    0.40
     runs
    0.38
     fisica
    0.38
     drips
    0.37
     consum
    0.35
     hayas
    0.35
     run
    0.35
    ించాలి
    0.35
    POSITIVE LOGITS
     ڈاکٹر
    0.45
    ቴ
    0.44
     ওয়ার
    0.44
     டாக்டர்
    0.41
     Oatmeal
    0.40
     አንዳንድ
    0.39
    Ἰ
    0.39
    
    0.39
    GetObject
    0.39
     عقب
    0.38
    Activations Density 0.010%

    No Known Activations