© 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. 9644
    Prev
    Next
    INDEX
    Explanations

    words following punctuation

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

    punctuation followed by explanation

    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
    及び
    0.37
     、
    0.34
    ൨
    0.34
    または
    0.34
    ܘܢ
    0.34
    ⵥ
    0.34
    ン
    0.33
    ᡧ
    0.33
    𒋫
    0.33
    ﺪ
    0.32
    POSITIVE LOGITS
     The
    0.48
     Although
    0.46
     Despite
    0.45
     After
    0.44
     There
    0.43
     If
    0.42
     As
    0.42
     although
    0.42
     People
    0.42
     despite
    0.41
    Activations Density 0.372%

    No Known Activations