© 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. 18412
    Prev
    Next
    INDEX
    Explanations

    selected state or selection

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

    selected and submitted

    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
     Durchmesser
    0.47
    QTTR
    0.47
    RAMM
    0.47
    OLYBD
    0.46
    LPTMR
    0.43
    OUND
    0.42
    瑆
    0.42
    AMPLES
    0.41
     நிறுவ
    0.40
    纍
    0.40
    POSITIVE LOGITS
    getSelected
    0.72
     selected
    0.71
     выбран
    0.71
    selected
    0.68
    checkbox
    0.67
     Selected
    0.66
    clicked
    0.66
     clicked
    0.64
     checkbox
    0.61
     inputted
    0.60
    Activations Density 0.004%

    No Known Activations