© 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. 33031
    Prev
    Next
    INDEX
    Explanations

    Arrest, introduction, background

    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
     using
    -1.37
     Desenvolvimento
    -1.21
     two
    -1.16
     his
    -1.12
     an
    -1.12
     with
    -1.10
     Kommune
    -1.09
     before
    -1.08
     Ensino
    -1.07
     any
    -1.03
    POSITIVE LOGITS
    paravant
    1.13
    hoots
    1.10
     RECOMMEND
    1.06
     イエロー
    1.06
     vérifier
    1.05
     vissa
    1.04
    owały
    1.03
     заявил
    1.02
    ㈬
    1.02
     acepción
    1.00
    Activations Density 0.009%

    No Known Activations