© 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. 240992
    Prev
    Next
    INDEX
    Explanations

    being photographed

    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
     gauge
    0.47
    綜合
    0.46
     marathon
    0.44
     empirically
    0.44
     -
    0.43
     Samaritan
    0.43
    综合
    0.43
    াইট
    0.42
     metaphys
    0.41
    gauge
    0.41
    POSITIVE LOGITS
     बेच
    0.51
     नाराजगी
    0.50
     Coding
    0.48
    稆
    0.47
     Financing
    0.47
     بیچ
    0.47
    害
    0.46
     mismanagement
    0.46
     ระบบ
    0.46
     而且
    0.46
    Activations Density 0.000%

    No Known Activations