© 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. 64609
    Prev
    Next
    INDEX
    Explanations

    low energy

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

    German words like 'für'

    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
    豸
    0.51
     oxide
    0.49
    typeof
    0.45
    authUser
    0.45
     cany
    0.45
    suppliers
    0.45
    multiSelectList
    0.44
     Oxide
    0.44
     Tufts
    0.44
    resourceUrl
    0.43
    POSITIVE LOGITS
     frü
    0.47
    w
    0.45
     för
    0.44
    讽
    0.44
     für
    0.43
     zur
    0.42
    god
    0.41
     GOD
    0.41
     bli
    0.41
    p
    0.40
    Activations Density 0.000%

    No Known Activations