© 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. 40799
    Prev
    Next
    INDEX
    Explanations

    foreign words and punctuation

    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
    ever
    0.48
    man
    0.47
    work
    0.45
    h
    0.45
    small
    0.45
     swallow
    0.45
    knit
    0.44
    formance
    0.43
    S
    0.42
    time
    0.41
    POSITIVE LOGITS
    <unused2179>
    0.57
    恶意
    0.50
    يد
    0.47
     intervenir
    0.47
     заболеваний
    0.47
     leider
    0.47
     गोद
    0.46
     плохо
    0.46
     respectivas
    0.45
     ولكن
    0.45
    Activations Density 0.002%

    No Known Activations