© 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-3-12B-IT
    5. 41-GEMMASCOPE-2-RES-65K
    7. 1446
    Prev
    Next
    INDEX
    Explanations

    estimate or calculate

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_41_width_65k_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
     compounded
    0.62
     compound
    0.60
     Compound
    0.57
    Compound
    0.56
     compounding
    0.55
    <unused55>
    0.54
    饗
    0.52
     assigned
    0.49
    compound
    0.49
     registrado
    0.49
    POSITIVE LOGITS
    Rough
    1.05
     rough
    0.99
     approximation
    0.97
     Rough
    0.97
    粗
    0.96
    approximation
    0.95
     calculate
    0.91
     estimate
    0.91
    calculate
    0.90
     Approximation
    0.90
    Activations Density 0.004%

    No Known Activations