© 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. 53091
    Prev
    Next
    INDEX
    Explanations

    goals conceded

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

    comparisons and access to information

    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
    TempBuffer
    0.54
    嬅
    0.50
     ካ
    0.50
    WindowManager
    0.48
    hiqdev
    0.48
    磪
    0.47
    imgInit
    0.46
    ொரு
    0.46
    𝐊
    0.46
    BackendAuth
    0.45
    POSITIVE LOGITS
     learns
    0.47
    ↵
    0.47
     at
    0.47
     than
    0.45
    dough
    0.44
     recognizes
    0.44
     thinks
    0.42
     sculpting
    0.42
     skeptical
    0.42
     cigars
    0.42
    Activations Density 0.000%

    No Known Activations