© 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. 23162
    Prev
    Next
    INDEX
    Explanations

    Direct list, finest work, nested IF

    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
    heavy
    0.46
    ",
    0.45
     ",
    0.45
    maximum
    0.44
    처
    0.42
    full
    0.42
     "
    0.41
    "
    0.41
     '
    0.41
     best
    0.41
    POSITIVE LOGITS
    ᵚ
    0.42
     rameaux
    0.41
    ौन
    0.41
    झ्या
    0.41
     डैश
    0.41
    ንሽ
    0.40
     noirâtre
    0.40
    зите
    0.40
    ्याच्या
    0.39
    መሪያ
    0.39
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.