© 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. 15663
    Prev
    Next
    INDEX
    Explanations

    which, where, that, how

    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
     короб
    -1.13
     pétrole
    -1.06
     vět
    -1.05
    ',
    -0.99
    Them
    -0.97
     lecteurs
    -0.97
    čno
    -0.96
    ⢇
    -0.95
     finalidad
    -0.94
     capuz
    -0.94
    POSITIVE LOGITS
     people
    1.35
     its
    1.29
     in
    1.20
     you
    1.16
     available
    1.15
     these
    1.06
     both
    1.04
     pueda
    1.04
     things
    1.03
     able
    1.02
    Activations Density 0.043%

    No Known Activations