© 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. 35918
    Prev
    Next
    INDEX
    Explanations

    gradually increase

    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
    Insurance
    0.44
    पुरा
    0.43
    ciudad
    0.42
    ួយ
    0.41
    র্পণ
    0.41
    Commerce
    0.40
    ଫ
    0.40
    insurance
    0.39
    дца
    0.38
    బ్
    0.38
    POSITIVE LOGITS
     Plot
    0.46
     Modules
    0.46
     README
    0.46
    README
    0.45
    izos
    0.45
     Aloe
    0.44
     optomet
    0.44
     Pet
    0.43
    \
    0.43
     Referee
    0.43
    Activations Density 0.002%

    No Known Activations