© 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. 36757
    Prev
    Next
    INDEX
    Explanations

    holiday greetings

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

    correlation and causation

    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
    Blob
    0.48
    Luis
    0.47
    Ste
    0.46
    Ener
    0.46
    や
    0.46
    Ar
    0.46
     și
    0.46
    D
    0.46
    &
    0.46
    ५
    0.46
    POSITIVE LOGITS
     Himalayas
    0.52
     Woh
    0.46
     कुठ
    0.46
     Algebraic
    0.45
     Nixon
    0.45
     binaries
    0.45
     Precambrian
    0.45
     anybody
    0.45
     Graphical
    0.45
     Bohr
    0.44
    Activations Density 0.000%

    No Known Activations