© 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. 202766
    Prev
    Next
    INDEX
    Explanations

    governance issues and access

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

    privileged domains and accounts

    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
     oran
    0.49
     musia
    0.49
     bild
    0.49
     foy
    0.48
     midden
    0.48
    志
    0.47
     yaad
    0.47
     interrom
    0.46
     carta
    0.46
     frein
    0.45
    POSITIVE LOGITS
     באמצעות
    0.52
    CAR
    0.48
    Gets
    0.47
    Climate
    0.47
    নার
    0.46
    GET
    0.46
    Algorithms
    0.46
    Situ
    0.45
     utilizing
    0.44
    ำ
    0.44
    Activations Density 0.000%

    No Known Activations