© 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. 15-GEMMASCOPE-2-RES-16K
    7. 2235
    Prev
    Next
    INDEX
    Explanations

    to be or wait for

    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_15_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
    agang
    0.84
     Merit
    0.77
    薯
    0.75
    phalt
    0.74
    slo
    0.72
    istry
    0.70
     gelt
    0.70
    aval
    0.68
     mink
    0.68
    ¯
    0.68
    POSITIVE LOGITS
    Ը
    1.52
    ujud
    1.46
    了一下
    1.42
     возвра
    1.41
     جنبي
    1.40
    ileri
    1.40
    Ț
    1.39
    geber
    1.38
    ByKey
    1.38
    峨
    1.37
    Activations Density 0.249%

    No Known Activations