© 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. 154181
    Prev
    Next
    INDEX
    Explanations

    as potential

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

    captivated Prince, preserving data

    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
    ún
    0.45
    ANGER
    0.45
    alions
    0.45
    ܝܢ
    0.44
    媺
    0.44
    ısının
    0.44
     половины
    0.44
    щер
    0.43
    үн
    0.42
    pherd
    0.41
    POSITIVE LOGITS
    従来の
    0.50
    8
    0.49
     چه
    0.46
    separated
    0.46
    state
    0.46
    4
    0.46
     quantification
    0.45
     fluctuation
    0.45
     razem
    0.45
     fluency
    0.44
    Activations Density 0.000%

    No Known Activations