© 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. 24648
    Prev
    Next
    INDEX
    Explanations

    specific word collocations

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

    Deformation, prevent, roid, white, cold, titles, fun, golden, Knight

    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
    的
    0.54
     مرتبط
    0.53
    ول
    0.52
    聯繫
    0.48
    equiv
    0.47
    ות
    0.46
    いる
    0.45
    의
    0.45
     marginalized
    0.44
     근
    0.44
    POSITIVE LOGITS
     njegova
    0.54
     jego
    0.50
     untersucht
    0.50
     vendu
    0.50
     yatırım
    0.48
     துரு
    0.48
    jego
    0.48
     wodurch
    0.47
     weist
    0.47
    𒋫
    0.47
    Activations Density 0.000%

    No Known Activations