© 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. 12699
    Prev
    Next
    INDEX
    Explanations

    describing someone's appearance or action

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

    you doing something

    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
     mercanc
    0.43
     dựa
    0.41
     επίπε
    0.40
    lty
    0.39
     त्यानुसार
    0.39
     τῶν
    0.38
    LOG
    0.37
    ⎪
    0.37
     succede
    0.37
    KEEP
    0.37
    POSITIVE LOGITS
     performing
    0.76
     wearing
    0.74
     모습
    0.69
     dressed
    0.63
    wearing
    0.63
     posing
    0.61
     Wearing
    0.61
     smiling
    0.61
     reciting
    0.61
    Wearing
    0.60
    Activations Density 0.085%

    No Known Activations