© 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. 101539
    Prev
    Next
    INDEX
    Explanations

    "Return the" or "Returns the"

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

    functions that return values

    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
    '
    0.84
    _
    0.77
    高兴
    0.71
    ι
    0.70
    ح
    0.68
    ។
    0.68
     ประก
    0.64
     directorio
    0.64
    ):
    0.64
     reiterated
    0.63
    POSITIVE LOGITS
    as
    1.06
    n
    1.05
    ia
    0.86
    sample
    0.79
    signal
    0.79
    data
    0.76
    ap
    0.73
     Return
    0.73
    am
    0.71
    value
    0.71
    Activations Density 0.020%

    No Known Activations