© 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. 31-GEMMASCOPE-2-RES-262K
    7. 51167
    Prev
    Next
    INDEX
    Explanations

    negative sentiment and numbers

    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_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
    language
    0.50
    H
    0.50
    ag
    0.49
    C
    0.48
    M
    0.47
    B
    0.46
    em
    0.46
    AS
    0.45
     also
    0.44
    T
    0.44
    POSITIVE LOGITS
     anus
    0.54
     multiSelectList
    0.46
     niss
    0.46
     uttering
    0.46
     ij
    0.43
     adik
    0.43
    æk
    0.43
     لیست
    0.42
     frauen
    0.42
    ష్ట
    0.42
    Activations Density 0.001%

    No Known Activations