© 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. 71561
    Prev
    Next
    INDEX
    Explanations

    technical terms and examples

    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
    t
    0.55
    run
    0.50
    persistent
    0.48
    led
    0.47
    arm
    0.47
    strong
    0.46
    rising
    0.45
    ract
    0.44
    load
    0.44
    dot
    0.44
    POSITIVE LOGITS
     Dispute
    0.56
     gewählt
    0.56
    يں
    0.55
     három
    0.52
     permesso
    0.52
    ﮈ
    0.51
     insgesamt
    0.51
     construc
    0.51
     bzw
    0.50
     ServicePolicy
    0.50
    Activations Density 0.001%

    No Known Activations