© 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. 57418
    Prev
    Next
    INDEX
    Explanations

    advertised price or aspiring minds

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

    transitions, progress, cultivate

    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
    查
    0.55
    梭
    0.55
    ->
    0.47
    /
    0.45
    Expansion
    0.44
     afficher
    0.44
    考
    0.43
     weib
    0.42
    骚
    0.42
    Teen
    0.41
    POSITIVE LOGITS
     교수
    0.61
    është
    0.57
     ಜನರು
    0.56
     제거
    0.54
     ලෙස
    0.53
    훨
    0.51
     판단
    0.50
    interpreter
    0.49
     ἡ
    0.48
     हिस्से
    0.48
    Activations Density 0.000%

    No Known Activations