© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 183945
    Prev
    Next
    INDEX
    Explanations

    teaching models and recipients

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

    benefits, links, teaching, UI

    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
    ିକ
    0.54
    uiDesigner
    0.49
    chrane
    0.48
     triunfo
    0.46
    ৪
    0.45
    beatCounter
    0.44
    एक्स
    0.44
    畩
    0.44
     वाय
    0.43
     victorias
    0.43
    POSITIVE LOGITS
     al
    0.51
     inev
    0.50
     Gent
    0.50
     ketiga
    0.50
     model
    0.49
     Teaching
    0.48
     recipient
    0.48
     Educ
    0.47
     Komm
    0.47
     Gentiles
    0.46
    Activations Density 0.002%

    No Known Activations