© 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. 241040
    Prev
    Next
    INDEX
    Explanations

    strips together, they did, those conditions

    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
    í
    0.54
    usahaan
    0.50
    anstalt
    0.47
    ne
    0.47
    elen
    0.47
     заслу
    0.45
     ಮತ್ತ
    0.45
    institut
    0.45
    ૬
    0.45
     더욱
    0.44
    POSITIVE LOGITS
     Đi
    0.53
    Eine
    0.50
     flop
    0.49
     Tutti
    0.48
    گی
    0.48
     Semua
    0.48
     soapy
    0.47
     cinemas
    0.46
     devs
    0.46
     tuoi
    0.46
    Activations Density 0.000%

    No Known Activations