© 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. 142426
    Prev
    Next
    INDEX
    Explanations

    fireworks cab health record Roblox

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

    conditional intros and examples

    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
    те
    0.59
    д
    0.59
     твор
    0.54
     eukary
    0.54
     inappropriately
    0.53
     verzi
    0.52
    твы
    0.52
     impairs
    0.52
    បែ
    0.52
    ж
    0.52
    POSITIVE LOGITS
    G
    0.57
    B
    0.55
    F
    0.55
    Ses
    0.54
    S
    0.52
    ید
    0.49
    R
    0.48
    Rit
    0.47
    Montserrat
    0.47
    Black
    0.47
    Activations Density 0.000%

    No Known Activations