© 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. 84504
    Prev
    Next
    INDEX
    Explanations

    adding hardware

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

    united several, but ultimately

    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
    =$(
    0.54
    ={\
    0.49
    ="("
    0.48
     handbags
    0.48
    =\
    0.48
     leggings
    0.47
    ່ນ
    0.46
    }$(
    0.46
     Sneakers
    0.46
     memorabilia
    0.45
    POSITIVE LOGITS
    Boolean
    0.46
    phy
    0.45
    map
    0.44
     Hal
    0.44
    ସ
    0.44
    மர
    0.44
    หลากหลาย
    0.44
    os
    0.43
    মাই
    0.43
    aires
    0.43
    Activations Density 0.000%

    No Known Activations