© 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-65K
    7. 2767
    Prev
    Next
    INDEX
    Explanations

    specific words

    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_65k_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
     Studien
    0.50
    ↵↵
    0.46
     Möglichkeiten
    0.45
    <h2>
    0.42
     Zudem
    0.41
     Після
    0.41
     yoki
    0.40
     (
    0.40
     เช่น
    0.40
    <0x0D>
    0.39
    POSITIVE LOGITS
    oretically
    0.74
    odore
    0.56
     and
    0.50
    berly
    0.46
     essential
    0.45
     in
    0.44
    نے
    0.43
     for
    0.43
    щото
    0.42
     inay
    0.42
    Activations Density 0.145%

    No Known Activations