© 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. 132281
    Prev
    Next
    INDEX
    Explanations

    regarding the

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

    open weights

    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
     LOW
    0.51
    𢎞
    0.50
    FIED
    0.50
    ěstí
    0.47
     concili
    0.47
     antidote
    0.47
     Approve
    0.47
     Large
    0.46
     fittest
    0.46
    ించాలి
    0.46
    POSITIVE LOGITS
    ográfica
    0.57
    uther
    0.49
    loc
    0.49
    ↵
    0.47
    film
    0.45
    auth
    0.45
    gaz
    0.44
    gment
    0.43
    ادية
    0.43
    andt
    0.43
    Activations Density 0.000%

    No Known Activations