© 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. 145376
    Prev
    Next
    INDEX
    Explanations

    others, alumnus, objective, digital, mean

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

    ranking and comparisons

    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
    L
    0.56
    there
    0.52
    Den
    0.52
    Dest
    0.51
    Cuando
    0.51
    A
    0.50
    Drop
    0.49
    ∀
    0.49
    Din
    0.49
    Ok
    0.48
    POSITIVE LOGITS
     magnificent
    0.51
     gmin
    0.44
    起こ
    0.44
    ToFile
    0.43
     gubernatorial
    0.43
    ंजा
    0.43
    riminating
    0.42
     contingency
    0.42
     amusing
    0.42
    移行
    0.42
    Activations Density 0.001%

    No Known Activations