© 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. 49479
    Prev
    Next
    INDEX
    Explanations

    specific pairings of words

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

    open-source model

    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
    O
    0.61
    Approved
    0.50
    udev
    0.50
    CAL
    0.50
    Y
    0.49
    Tec
    0.48
    ㄥ
    0.48
    approve
    0.47
    imgur
    0.47
    I
    0.47
    POSITIVE LOGITS
     tamam
    0.48
    льний
    0.46
     mobilized
    0.44
    ؛
    0.44
     strainer
    0.43
     ख
    0.43
     شعب
    0.43
     системати
    0.41
     belge
    0.41
     poultry
    0.41
    Activations Density 0.000%

    No Known Activations