© 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. 95095
    Prev
    Next
    INDEX
    Explanations

    stating the obvious

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

    obvious or clear statements

    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
     confirmé
    0.70
     +,
    0.67
     można
    0.66
     määr
    0.66
     as
    0.65
     confirm
    0.64
     confirmado
    0.63
    ١
    0.63
     ascertaining
    0.63
     ,"
    0.61
    POSITIVE LOGITS
    henko
    0.73
    显然
    0.69
    '
    0.68
    明显
    0.63
    ா
    0.59
    ਾ
    0.55
    ка
    0.54
    不是
    0.54
    chtigen
    0.54
    并不是
    0.54
    Activations Density 0.051%

    No Known Activations