© 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. 46527
    Prev
    Next
    INDEX
    Explanations

    click to reveal or view

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

    provides options and versions

    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
     Township
    0.47
    !”
    0.46
    didn
    0.45
    開業
    0.44
    iding
    0.43
    instead
    0.43
    jama
    0.42
     !
    0.42
     !!!
    0.42
    !.
    0.42
    POSITIVE LOGITS
     ఇతర
    0.46
     PROVID
    0.45
     endpoints
    0.44
     facil
    0.44
    資格
    0.44
    资格
    0.43
     prestataire
    0.43
     QUAL
    0.42
     easements
    0.42
    诱
    0.41
    Activations Density 0.001%

    No Known Activations