© 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. 104343
    Prev
    Next
    INDEX
    Explanations

    from X to Y transition

    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
    corrhi
    -1.27
     любы
    -1.19
     particular
    -1.19
    うまい
    -1.12
    unlike
    -1.12
     élo
    -1.08
     these
    -1.07
     rozwój
    -1.07
     suelen
    -1.04
     oeufs
    -1.04
    POSITIVE LOGITS
     become
    1.41
     became
    1.23
     becoming
    1.22
     becomes
    1.20
     being
    1.20
    ΩΝ
    1.20
     более
    1.12
     Menjadi
    1.12
     veritable
    1.08
     intim
    1.06
    Activations Density 0.025%

    No Known Activations