© 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. 115320
    Prev
    Next
    INDEX
    Explanations

    legal, technical, and business terms

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

    limiting liability and personal protection

    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
    g
    0.53
     Secondary
    0.52
     Helper
    0.48
    t
    0.47
     Primary
    0.47
     And
    0.46
     How
    0.45
    d
    0.45
    model
    0.45
    trying
    0.44
    POSITIVE LOGITS
     bese
    0.49
     diminution
    0.48
     columna
    0.47
     konz
    0.46
     rique
    0.46
     alumina
    0.45
     irrevoc
    0.45
     alarma
    0.45
     audiov
    0.45
     audiovis
    0.44
    Activations Density 0.000%

    No Known Activations