© 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. 75195
    Prev
    Next
    INDEX
    Explanations

    organizations and roles

    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
     emoji
    -1.28
     funktioniert
    -1.25
    pení
    -1.19
     selfie
    -1.16
     microbiome
    -1.15
     июня
    -1.15
     två
    -1.15
     onboarding
    -1.14
     seier
    -1.12
    IDADE
    -1.11
    POSITIVE LOGITS
    Leírás
    1.20
     sœur
    1.17
    Batt
    1.13
     soeur
    1.10
    dáms
    1.04
    䊊
    1.02
    Hvem
    1.00
     considerable
    0.99
    crowned
    0.98
     excellent
    0.98
    Activations Density 0.118%

    No Known Activations