© 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. 16-GEMMASCOPE-2-RES-262K
    7. 8383
    Prev
    Next
    INDEX
    Explanations

    python public def function

    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_16_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
    s
    0.42
    K
    0.39
    O
    0.35
    X
    0.34
    EN
    0.33
    N
    0.32
    al
    0.31
    S
    0.30
    D
    0.29
    ’
    0.29
    POSITIVE LOGITS
     تھا۔
    0.25
    :
    0.25
    icolored
    0.24
    ့
    0.23
     pliers
    0.23
    いません
    0.23
    다
    0.23
     tetrachloride
    0.23
     этими
    0.22
    عنی
    0.22
    Activations Density 0.239%

    No Known Activations