© 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. 66270
    Prev
    Next
    INDEX
    Explanations

    phrases specifying entities or actions

    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
     poë
    -1.39
     furia
    -1.29
     bluse
    -1.28
    が
    -1.23
     umbro
    -1.21
     eccl
    -1.19
     ادبی
    -1.12
    ⽼
    -1.12
     bicic
    -1.12
     tenda
    -1.11
    POSITIVE LOGITS
    をお願い
    1.47
     which
    1.42
    migrationBuilder
    1.41
    の方も
    1.30
     there
    1.30
     Audiodateien
    1.27
    umbered
    1.26
     妻
    1.23
    の方は
    1.23
    MediaStore
    1.23
    Activations Density 0.062%

    No Known Activations