© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 130042
    Prev
    Next
    INDEX
    Explanations

    id, value, size

    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
     during
    -1.31
     this
    -1.19
     września
    -1.16
     get
    -1.15
     who
    -1.15
     hacían
    -1.11
     until
    -1.06
     aims
    -1.05
     lutego
    -1.03
     just
    -1.02
    POSITIVE LOGITS
     ñ
    1.14
     minimalis
    1.11
    加热
    1.07
     ats
    1.05
    猎人
    1.04
     GETS
    1.04
    Interes
    1.03
     ony
    1.02
     verhind
    1.02
     possibilités
    1.02
    Activations Density 0.001%

    No Known Activations