© 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. 125620
    Prev
    Next
    INDEX
    Explanations

    find or locate

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

    online courses and research

    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
     TextAlign
    0.47
     Cristina
    0.44
    ગુ
    0.43
     எதி
    0.43
    Mercedes
    0.42
    THRESHOLD
    0.41
    Х
    0.41
     Lorenzo
    0.41
    უნქ
    0.40
     "").
    0.40
    POSITIVE LOGITS
    comput
    0.55
    value
    0.54
    izace
    0.54
    igated
    0.53
    en
    0.52
     uš
    0.52
     überprü
    0.52
    ized
    0.51
    u
    0.51
    et
    0.51
    Activations Density 0.000%

    No Known Activations