© 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. 227735
    Prev
    Next
    INDEX
    Explanations

    programs and services

    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
     উপলব্ধ
    0.46
    𖥔
    0.45
     Stellung
    0.44
     нужда
    0.44
     জীবনী
    0.44
    用户信息
    0.43
     ଯ
    0.43
    ahh
    0.43
    atthakath
    0.42
    喁
    0.42
    POSITIVE LOGITS
     pér
    0.51
    1
    0.50
    ’
    0.50
     accede
    0.49
     sectors
    0.48
    இவர்
    0.48
     secteur
    0.48
     practise
    0.47
    neighbor
    0.46
     question
    0.46
    Activations Density 0.001%

    No Known Activations