© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 12549
    Prev
    Next
    INDEX
    Explanations

    mathematical index i

    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
     However
    -1.09
     After
    -1.06
     Even
    -1.05
     hauptsächlich
    -1.04
     to
    -1.04
     something
    -1.02
     after
    -1.00
     As
    -1.00
     Some
    -0.99
     mainly
    -0.98
    POSITIVE LOGITS
     ledig
    1.29
     matières
    1.16
     combinación
    1.16
     différences
    1.11
     propriétés
    1.11
     matériaux
    1.11
     canaux
    1.02
     tissus
    1.02
     facteurs
    1.01
     qualités
    1.01
    Activations Density 0.011%

    No Known Activations