© 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. 158842
    Prev
    Next
    INDEX
    Explanations

    body environment reliability health

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

    limericks

    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
     prefixed
    0.44
    露
    0.43
     can
    0.43
     IBOutlet
    0.42
     Inhib
    0.41
    Converted
    0.41
     noticeable
    0.41
    男子
    0.41
    辛
    0.40
     Power
    0.40
    POSITIVE LOGITS
    phia
    0.55
    araja
    0.54
    tena
    0.52
    teau
    0.52
    athu
    0.52
    hia
    0.50
    fst
    0.50
     najman
    0.49
    uque
    0.48
    ,_-
    0.47
    Activations Density 0.000%

    No Known Activations