© 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. 89603
    Prev
    Next
    INDEX
    Explanations

    actions and deliverables

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

    problems and solutions

    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
    ement
    0.49
    Selling
    0.48
    Latest
    0.47
    Ｔ
    0.46
     windshield
    0.45
     наличие
    0.44
     اینکه
    0.43
     সত্ত
    0.43
    とおり
    0.42
    o
    0.42
    POSITIVE LOGITS
     возника
    0.54
     dzie
    0.48
     Computing
    0.46
     лекар
    0.44
     Tsch
    0.43
    CCD
    0.42
    禧
    0.42
     gesam
    0.42
     biomed
    0.41
     Sonn
    0.41
    Activations Density 0.001%

    No Known Activations