© 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. 65011
    Prev
    Next
    INDEX
    Explanations

    holiday greetings and closings

    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
     about
    -1.26
     at
    -1.23
     similar
    -1.21
     within
    -1.20
     given
    -1.17
     such
    -1.11
     detailed
    -1.06
    句话
    -1.06
     previous
    -1.05
     typical
    -1.05
    POSITIVE LOGITS
     everyone
    1.35
    Whatever
    1.33
     kaikk
    1.31
     prendra
    1.22
     всички
    1.22
    everyone
    1.21
    Everyone
    1.17
     meren
    1.17
     ordre
    1.16
     relâche
    1.15
    Activations Density 0.014%

    No Known Activations