© 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. 86309
    Prev
    Next
    INDEX
    Explanations

    service provider

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

    explaining riddles and definitions

    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
    Ｃ
    0.49
    䡋
    0.46
    ಹಿ
    0.43
     архівів
    0.42
    𝟎
    0.42
     LOUIS
    0.42
    بور
    0.42
    ରି
    0.41
     analysing
    0.41
     estremamente
    0.41
    POSITIVE LOGITS
    s
    0.54
     b
    0.52
    ed
    0.47
    value
    0.45
     symmetrical
    0.45
    speed
    0.44
    screen
    0.43
    aime
    0.43
     redefined
    0.43
     вза
    0.42
    Activations Density 0.000%

    No Known Activations