© 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. 22750
    Prev
    Next
    INDEX
    Explanations

    overline or bar symbol

    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
    শ
    0.50
     aspetto
    0.49
    ש
    0.49
     êtes
    0.47
    את
    0.46
     opérations
    0.45
     אני
    0.45
    老闆
    0.45
    ༸
    0.45
    ন্দর
    0.45
    POSITIVE LOGITS
    парта
    0.48
    <0xB7>
    0.47
    ur
    0.46
    тор
    0.45
    ić
    0.44
    тори
    0.43
     Pear
    0.43
    प्रिल
    0.42
    nity
    0.42
    抬
    0.42
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.