© 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. 194470
    Prev
    Next
    INDEX
    Explanations

    available october

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

    impacting areas, server launched, hair caressing

    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
     pann
    0.47
     bals
    0.46
     bruke
    0.46
    想
    0.45
    知道了
    0.44
     fizer
    0.43
     enfermed
    0.42
     ministra
    0.42
     stalling
    0.42
    遇到了
    0.41
    POSITIVE LOGITS
    lə
    0.55
    İL
    0.51
     ছিল
    0.50
     witty
    0.50
    ה
    0.50
    ūs
    0.49
     गुलाम
    0.49
    ação
    0.48
     विनय
    0.48
    ία
    0.48
    Activations Density 0.000%

    No Known Activations