© 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. 226246
    Prev
    Next
    INDEX
    Explanations

    child care

    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
    ი
    0.49
    ింది
    0.47
    ък
    0.47
     също
    0.45
    ()}.
    0.45
    রত
    0.45
     свого
    0.45
    জে
    0.44
    镶
    0.44
     וב
    0.44
    POSITIVE LOGITS
    0.57
     leverage
    0.53
     timestamps
    0.52
     plausible
    0.49
     more
    0.48
     use
    0.48
     believable
    0.48
     adaptability
    0.47
     DSC
    0.47
     rys
    0.47
    Activations Density 0.007%

    No Known Activations