© 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. 1301
    Prev
    Next
    INDEX
    Explanations

    month journey

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

    increase dividends

    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
    ༧
    0.36
    ༠
    0.35
    Გ
    0.35
    TARGETTING
    0.34
    ༢
    0.33
    Მ
    0.33
    Კ
    0.33
    ᆭ
    0.33
    URNIZ
    0.32
    ༨
    0.32
    POSITIVE LOGITS
     (
    0.51
    ,
    0.50
    0.49
     with
    0.46
     and
    0.45
     B
    0.45
     A
    0.44
     on
    0.43
     S
    0.42
     &
    0.41
    Activations Density 0.358%

    No Known Activations