© 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-3-1B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 4033
    Prev
    Next
    INDEX
    Explanations

    letter followed by punctuation or abbreviation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_22_width_16k_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
    2.48
    R
    2.11
    T
    2.07
    C
    2.06
    D
    1.98
    P
    1.93
    E
    1.83
    M
    1.82
    L
    1.57
    A
    1.55
    POSITIVE LOGITS
    多彩
    0.66
    ئين
    0.65
    will
    0.63
    目に
    0.63
     घायल
    0.62
     Fund
    0.61
    相談
    0.60
    Initializer
    0.59
    tilde
    0.58
    被
    0.58
    Activations Density 0.513%

    No Known Activations