© 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. 49005
    Prev
    Next
    INDEX
    Explanations

    most descriptive words

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

    AI transformer models

    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
     полностью
    0.49
     повністю
    0.46
    Drake
    0.45
    虽然
    0.45
    ጁ
    0.44
    Ste
    0.44
     οποίο
    0.44
     intégré
    0.44
    Seth
    0.44
    F
    0.44
    POSITIVE LOGITS
     toc
    0.60
     simplification
    0.54
     sufferings
    0.54
     theses
    0.53
     luminescence
    0.52
     flatness
    0.52
     sampel
    0.51
     datos
    0.50
     recursion
    0.49
     repetitions
    0.49
    Activations Density 0.000%

    No Known Activations