© 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. 158624
    Prev
    Next
    INDEX
    Explanations

    official announcements and launches

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

    official public information

    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
    Occasionally
    0.42
    த்
    0.41
    에요
    0.40
    ،
    0.39
    т
    0.39
    ﺗ
    0.38
    에서
    0.38
    ="
    0.38
    Después
    0.38
    偶尔
    0.38
    POSITIVE LOGITS
     publicit
    0.54
     pemasaran
    0.50
     prostu
    0.49
     offizi
    0.48
     Official
    0.47
     flashy
    0.46
     officielle
    0.46
     actual
    0.46
     fanfare
    0.46
     நேரடியாக
    0.46
    Activations Density 0.003%

    No Known Activations