© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 33971
    Prev
    Next
    INDEX
    Explanations

    address numbers and street names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pérd
    -1.17
     guir
    -1.16
     menyen
    -1.13
    эф
    -1.13
    комплект
    -1.11
     lampe
    -1.10
     bluse
    -1.10
    痪
    -1.09
    providedIn
    -1.09
     skrev
    -1.09
    POSITIVE LOGITS
     variously
    1.09
    it
    1.06
     Teraz
    1.05
     feiner
    1.05
     trabalhadores
    1.01
    ay
    1.00
     obere
    1.00
    au
    0.97
    a
    0.97
     varones
    0.96
    Activations Density 0.005%

    No Known Activations