© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 112768
    Prev
    Next
    INDEX
    Explanations

    function calls, method chaining

    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
     Supervisors
    0.50
    髗
    0.49
     supervisors
    0.48
     warranties
    0.48
     έγινε
    0.46
     originality
    0.45
    ା
    0.45
     thefts
    0.44
     rekonstru
    0.44
     проходить
    0.44
    POSITIVE LOGITS
    sh
    0.59
    pt
    0.57
    la
    0.56
    los
    0.53
    sti
    0.50
    ll
    0.49
    s
    0.48
    lo
    0.47
    sa
    0.47
    scar
    0.47
    Activations Density 0.001%

    No Known Activations