© 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-3-270M
    5. 12-GEMMASCOPE-2-RES-16K
    7. 4044
    Prev
    Next
    INDEX
    Explanations

    requestUri

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_12_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
     пів
    0.87
     súper
    0.87
    énez
    0.84
    __:
    0.81
    }}^{(\
    0.78
    วจ
    0.75
    áus
    0.73
    더니
    0.71
     paraphrase
    0.68
    凖
    0.68
    POSITIVE LOGITS
    Bah
    1.75
    Bag
    1.69
    adar
    1.68
    Bog
    1.66
     Duis
    1.63
     Bog
    1.60
     Bauer
    1.60
     Bag
    1.59
    bord
    1.59
    Man
    1.57
    Activations Density 0.000%

    No Known Activations