© 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. 183552
    Prev
    Next
    INDEX
    Explanations

    household objects and materials

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

    volatile, volatile recently

    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
    कु
    0.55
    ပြင်
    0.52
    हा
    0.52
    กอง
    0.50
    श
    0.48
    𒇉
    0.48
    ક
    0.46
    ਗ
    0.46
    เช
    0.45
    ແ
    0.45
    POSITIVE LOGITS
    returned
    0.47
     stoj
    0.46
    )
    0.45
    i
    0.45
     ial
    0.45
     felled
    0.44
     intercom
    0.43
    ヽ
    0.43
     interpersonal
    0.43
     iridium
    0.43
    Activations Density 0.000%

    No Known Activations