© 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. 73328
    Prev
    Next
    INDEX
    Explanations

    new appointments

    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
    preneur
    -1.15
     nació
    -1.12
    特别是
    -1.06
    izate
    -1.05
    capulco
    -1.03
    这一幕
    -1.03
     originalen
    -1.03
     vermeiden
    -1.02
    зидент
    -1.02
    碓
    -1.01
    POSITIVE LOGITS
     who
    2.42
     people
    1.52
     capable
    1.41
     woman
    1.39
     female
    1.34
     assistant
    1.30
     someone
    1.30
     young
    1.27
     whom
    1.26
     person
    1.24
    Activations Density 0.052%

    No Known Activations