© 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. 40-GEMMASCOPE-2-RES-262K
    7. 134013
    Prev
    Next
    INDEX
    Explanations

    calculate or multiply

    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_40_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
    枤
    0.39
    达成
    0.38
    <unused382>
    0.36
    กา
    0.34
     जबर
    0.34
    znac
    0.32
    TURN
    0.32
    ጎ
    0.32
    Harry
    0.31
    NORTH
    0.31
    POSITIVE LOGITS
     lakhs
    0.48
     crore
    0.43
     histologic
    0.43
     lakh
    0.41
     phonon
    0.41
     crores
    0.40
     nonzero
    0.40
     kerala
    0.39
     redshift
    0.39
    ⁤
    0.38
    Activations Density 0.003%

    No Known Activations