© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 79105
    Prev
    Next
    INDEX
    Explanations

    disclosure agreement or franchise

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nedost
    0.44
     թվ
    0.43
     estre
    0.43
     correctes
    0.42
    耇
    0.42
     acel
    0.42
     mär
    0.42
     zdjęcia
    0.42
     numeri
    0.41
    整个
    0.41
    POSITIVE LOGITS
     warships
    0.48
    opening
    0.43
    /+
    0.43
    quoting
    0.43
    hc
    0.43
     वैशिष्ट
    0.43
    UDE
    0.42
     veteran
    0.42
    insular
    0.42
    Asia
    0.41
    Activations Density 0.004%

    No Known Activations