© 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
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 126785
    Prev
    Next
    INDEX
    Explanations

    following punctuation

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

    explanatory clauses or lists

    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
    瑄
    0.49
    습니다
    0.48
    tı
    0.47
    ங்க்
    0.46
     सारी
    0.46
     listy
    0.44
    亼
    0.44
    ே
    0.43
     sceGu
    0.43
    Develop
    0.42
    POSITIVE LOGITS
    atic
    0.44
     nan
    0.44
     presidents
    0.44
    ens
    0.43
    ruciating
    0.43
    rock
    0.42
    ont
    0.42
     trending
    0.42
     On
    0.42
    on
    0.41
    Activations Density 0.000%

    No Known Activations