© 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. 100311
    Prev
    Next
    INDEX
    Explanations

    safety of individuals and characters

    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
    st
    0.54
    line
    0.52
    on
    0.50
    an
    0.48
    static
    0.48
    destination
    0.46
    p
    0.44
    transformation
    0.44
    美
    0.43
    sem
    0.43
    POSITIVE LOGITS
    CardArray
    0.49
     celý
    0.43
     suv
    0.43
     wund
    0.43
     stuffing
    0.42
     conducteur
    0.42
     ngủ
    0.42
    ätte
    0.41
     cardinals
    0.41
     latéraux
    0.40
    Activations Density 0.002%

    No Known Activations