© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 13763
    Prev
    Next
    INDEX
    Explanations

    get the information

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

    a specific age or context

    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_16k_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
    ilización
    0.48
    莺
    0.47
    Positions
    0.46
    不稳定
    0.46
     있어야
    0.45
     있도록
    0.44
    itinéraire
    0.42
    لیفون
    0.41
    ichiro
    0.41
    多个
    0.41
    POSITIVE LOGITS
     twee
    0.50
     ii
    0.49
    趄
    0.47
     vak
    0.46
     chương
    0.46
     bitch
    0.46
     dynamo
    0.44
     crappy
    0.44
     shitty
    0.44
     fave
    0.44
    Activations Density 0.002%

    No Known Activations