© 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. 204018
    Prev
    Next
    INDEX
    Explanations

    Download , security , options , securely , next morning , sleeping processes , Download manually

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

    planning review courses freelancers

    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
     ước
    0.50
    istern
    0.49
     ``
    0.45
    ledem
    0.45
    ı
    0.44
    opencamera
    0.44
    op
    0.43
     landlord
    0.43
     ''.
    0.43
     svojoj
    0.43
    POSITIVE LOGITS
     hochwertige
    0.62
    Adaptive
    0.48
    Celebr
    0.47
    个性
    0.46
     Интернет
    0.46
    Porter
    0.45
     पहना
    0.44
     hochwert
    0.44
    歼
    0.44
    Tennis
    0.44
    Activations Density 0.000%

    No Known Activations