© 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. 184267
    Prev
    Next
    INDEX
    Explanations

    borders and patterns

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

    descriptive qualifiers

    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
    0.52
    abhuto
    0.50
    ર
    0.49
     objet
    0.49
    า
    0.49
    withstanding
    0.48
     टूट
    0.48
    𝖆
    0.47
     antwort
    0.47
     haki
    0.47
    POSITIVE LOGITS
     چهار
    0.46
     فرش
    0.45
     flooring
    0.43
    Punch
    0.43
     heifer
    0.43
    Fuse
    0.43
    exponent
    0.43
    Hex
    0.42
    Border
    0.42
    Paw
    0.42
    Activations Density 0.000%

    No Known Activations