© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 4164
    Prev
    Next
    INDEX
    Explanations

    asking about you

    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
     vibrates
    0.40
    "{@
    0.36
    🕜
    0.35
    当社
    0.34
     Ecuadorian
    0.34
     ಸಂಧಿ
    0.34
    ២
    0.34
    撾
    0.33
     bypassing
    0.33
     suppresses
    0.32
    POSITIVE LOGITS
    out
    0.33
    ↵
    0.31
    ul
    0.30
    div
    0.30
     Div
    0.28
    h
    0.28
    sl
    0.28
     Gothic
    0.27
    if
    0.27
    f
    0.27
    Activations Density 0.000%

    No Known Activations