© 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. 51031
    Prev
    Next
    INDEX
    Explanations

    what time works

    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
    0.57
    ↵
    0.52
    }}
    0.47
             
    0.46
     У
    0.46
    akati
    0.45
    0.43
     Toto
    0.42
    也許
    0.42
     Ingram
    0.42
    POSITIVE LOGITS
    ကြောင့်
    0.51
    اونلو
    0.50
    queous
    0.46
     برقرار
    0.45
    হাসিক
    0.44
    मील
    0.44
    思维
    0.44
    <unused42>
    0.42
    <unused67>
    0.41
    वासीय
    0.41
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.