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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 201878
    Prev
    Next
    INDEX
    Explanations

    negative words followed by punctuation

    np_acts-logits-general · gemini-2.5-flash-lite

    collocations followed by specific words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    സ്ത
    0.54
    ൦
    0.51
    વતી
    0.48
    ջ
    0.47
    жами
    0.46
    퓰
    0.46
    堊
    0.46
     Dij
    0.45
    朶
    0.45
     Marius
    0.45
    POSITIVE LOGITS
    --
    0.48
    ulin
    0.46
    ...
    0.46
    ................
    0.44
    ...\...\...\...\
    0.43
    --------
    0.43
    ......
    0.43
    ench
    0.43
    rund
    0.43
     并
    0.42
    Activations Density 0.000%

    No Known Activations