© 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. 27483
    Prev
    Next
    INDEX
    Explanations

    although

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

    though

    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
     hati
    0.54
    transpose
    0.53
    cause
    0.52
    ”]
    0.52
     câ
    0.52
     upheaval
    0.50
    之间的
    0.50
    くて
    0.49
     l
    0.49
     दिल
    0.49
    POSITIVE LOGITS
    ED
    0.76
     물론
    0.71
     oczywiście
    0.70
    ਰ
    0.69
    of
    0.65
    Aunque
    0.64
    ا
    0.64
    Avec
    0.63
    מ
    0.63
    También
    0.61
    Activations Density 0.044%

    No Known Activations