© 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. 84728
    Prev
    Next
    INDEX
    Explanations

    questions about

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

    languages and code

    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
     critical
    0.54
     programmatic
    0.51
    经历
    0.48
     microwave
    0.46
    缠
    0.46
     deliberate
    0.46
     high
    0.45
     forceful
    0.45
     meaningful
    0.45
     counter
    0.45
    POSITIVE LOGITS
    ukiyoe
    0.59
    rå
    0.55
    lfloor
    0.53
    ༠
    0.53
    )^{-\
    0.51
    )^{
    0.50
     trauer
    0.50
    )^{-
    0.50
    åg
    0.49
    stargo
    0.49
    Activations Density 0.001%

    No Known Activations