© 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. 210983
    Prev
    Next
    INDEX
    Explanations

    preparation and instructions

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

    lists, items, or specific data

    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
    ♰
    0.52
     фаразлары
    0.49
    ⌔
    0.49
    すご
    0.49
     sít
    0.48
    ፎ
    0.47
    ፫
    0.47
    πε
    0.47
    ྵ
    0.47
    ოვ
    0.47
    POSITIVE LOGITS
    0.63
     Product
    0.58
     Health
    0.54
     Authentication
    0.53
     Travel
    0.50
     Int
    0.49
     Diabetic
    0.47
                   
    0.46
     Group
    0.46
     Download
    0.46
    Activations Density 0.000%

    No Known Activations