© 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. 139561
    Prev
    Next
    INDEX
    Explanations

    clinical trials, PayPal transactions

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

    underlying power and champions

    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
    యి
    0.52
    ye
    0.51
    ną
    0.50
    ici
    0.47
    키
    0.47
    극
    0.47
     Gratis
    0.45
     Noyes
    0.44
    용
    0.44
    2
    0.43
    POSITIVE LOGITS
     നടന്ന
    0.47
    ман
    0.46
    ittal
    0.45
    товано
    0.45
     prick
    0.44
    ძლიათ
    0.43
    шта
    0.43
    шан
    0.43
     పిల్ల
    0.43
    frequencies
    0.43
    Activations Density 0.000%

    No Known Activations