© 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. 104896
    Prev
    Next
    INDEX
    Explanations

    punctuation separating clauses

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

    separating clauses with 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
    *;
    0.54
    with
    0.54
    which
    0.52
     with
    0.51
    }$;
    0.50
    ?;
    0.50
    ;<
    0.48
     which
    0.46
    ;</
    0.46
     Firstly
    0.46
    POSITIVE LOGITS
    ين
    0.52
    swick
    0.42
     Naciones
    0.42
    다
    0.40
    insuku
    0.40
    dür
    0.39
    dır
    0.38
     alrededores
    0.38
    ा
    0.38
    ją
    0.38
    Activations Density 0.025%

    No Known Activations