© 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. 26624
    Prev
    Next
    INDEX
    Explanations

    laws and rules

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

    AI analysis

    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
    дает
    0.45
     foyer
    0.44
     weights
    0.42
    :
    0.41
    онов
    0.41
     steering
    0.40
     examen
    0.40
    <sup>
    0.40
    험
    0.39
     fringes
    0.39
    POSITIVE LOGITS
     ಕಾನೂ
    0.57
     ባህ
    0.53
     اکث
    0.49
     હવા
    0.49
     وک
    0.47
     പിന്ന
    0.47
     ನಾಗ
    0.47
     আইন
    0.47
    rą
    0.46
     قوانین
    0.46
    Activations Density 0.000%

    No Known Activations