© 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. 212679
    Prev
    Next
    INDEX
    Explanations

    specific entities or events

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

    breathing effect

    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
     pourtant
    0.49
     reconnu
    0.48
     ഗ
    0.47
    手动
    0.46
     nó
    0.46
     Phone
    0.46
     wur
    0.45
     كال
    0.45
     categ
    0.45
     나와
    0.44
    POSITIVE LOGITS
    ibalsan
    0.47
    ุปกรณ์
    0.46
    João
    0.45
    ’,
    0.44
    FBSDKInternal
    0.44
    ोष
    0.44
    ␥
    0.44
    :'],
    0.43
    multirow
    0.43
    relativistic
    0.43
    Activations Density 0.000%

    No Known Activations