© 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-3-270M-IT
    5. 15-GEMMASCOPE-2-RES-262K
    7. 69782
    Prev
    Next
    INDEX
    Explanations

    cell in formula

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_15_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
    禪
    1.06
     daimyo
    1.04
    ísica
    1.02
     shogun
    1.00
     porcel
    1.00
     nibb
    0.99
     nœ
    0.98
     koa
    0.98
    ategory
    0.97
    ומי
    0.96
    POSITIVE LOGITS
     research
    1.53
     UNDP
    1.52
     testing
    1.52
     Armstrong
    1.50
     A
    1.48
     Conservative
    1.43
     Har
    1.43
     Bet
    1.42
     R
    1.41
     Agri
    1.40
    Activations Density 0.044%

    No Known Activations