© 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. 56967
    Prev
    Next
    INDEX
    Explanations

    requires improvement, halts between, band intensity

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

    Poiseuille, camera, scaling, search

    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
     মাহ
    0.48
     तुमसे
    0.48
    gc
    0.47
     ڪري
    0.47
     እንቅስቃሴ
    0.47
    n
    0.46
     CLUB
    0.46
     Lebensmittel
    0.45
     አል
    0.45
     забы
    0.45
    POSITIVE LOGITS
    ça
    0.46
    ре
    0.45
    şa
    0.45
    US
    0.44
    हाला
    0.44
    ുകളാണ്
    0.44
    顕
    0.43
    iD
    0.42
    Six
    0.42
    Liber
    0.42
    Activations Density 0.000%

    No Known Activations