© 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. 100670
    Prev
    Next
    INDEX
    Explanations

    how to

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

    characteristics and behaviors

    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
     soldados
    0.54
    స్వా
    0.52
    승
    0.48
    隨
    0.46
    DeviceCompliance
    0.46
    '=>'','
    0.46
    ementara
    0.46
     comunicado
    0.44
    mert
    0.44
    tsc
    0.43
    POSITIVE LOGITS
     ce
    0.46
     behaviors
    0.45
     visc
    0.44
     bâtiment
    0.44
     CE
    0.43
     inpatient
    0.43
     acumen
    0.42
    ⵖ
    0.42
     Behav
    0.41
    行う
    0.41
    Activations Density 0.002%

    No Known Activations