© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 4490
    Prev
    Next
    INDEX
    Explanations

    discussing actions and focus

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    一
    0.59
     a
    0.56
     quando
    0.55
     c
    0.52
     problema
    0.52
     pergunta
    0.47
    pu
    0.47
     n
    0.46
    ponen
    0.46
    bor
    0.45
    POSITIVE LOGITS
    MathMarks
    0.55
     imputation
    0.48
     precincts
    0.47
    isLen
    0.47
     jurisdictions
    0.46
     borders
    0.45
     outfits
    0.45
     veille
    0.45
    '}}>
    0.45
    withstanding
    0.44
    Activations Density 0.000%

    No Known Activations