© 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. 89499
    Prev
    Next
    INDEX
    Explanations

    Kul and specific followed words

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

    established trends

    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
     potentially
    0.51
    ριο
    0.47
     no
    0.44
     Seismic
    0.44
    う
    0.43
     seismic
    0.43
     podría
    0.43
    认为
    0.41
     cannot
    0.41
    argin
    0.40
    POSITIVE LOGITS
    h
    0.54
     Kul
    0.54
     сты
    0.52
     kul
    0.49
     शौ
    0.49
    Kul
    0.49
     wasser
    0.47
    ถา
    0.47
     KL
    0.46
    स्टैंड
    0.46
    Activations Density 0.000%

    No Known Activations