© 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. 33746
    Prev
    Next
    INDEX
    Explanations

    bundle or bibliography marker

    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
     any
    -1.76
     However
    -1.38
     when
    -1.38
     anything
    -1.30
     WITH
    -1.28
     if
    -1.21
     щодо
    -1.20
     Even
    -1.17
     anyone
    -1.17
     With
    -1.17
    POSITIVE LOGITS
     remplacer
    1.22
     撮
    1.18
    を持っている
    1.16
     importación
    1.14
    küche
    1.14
     betaling
    1.13
    くらいで
    1.13
     entornos
    1.10
     elevación
    1.10
     الاث
    1.09
    Activations Density 0.000%

    No Known Activations