© 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. 10-GEMMASCOPE-RES-131K
    7. 40993
    Prev
    Next
    INDEX
    Explanations

    profanity endings

    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_10/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
    .
    -1.41
     estatus
    -1.21
    結局
    -1.21
    荚
    -1.20
    nonatomic
    -1.19
     بودم
    -1.12
    アプローチ
    -1.12
    äldrar
    -1.11
    缓解
    -1.10
    弔
    -1.10
    POSITIVE LOGITS
    をした
    1.30
    釹
    1.27
     כאשר
    1.27
     vivace
    1.23
    kozás
    1.23
    dyž
    1.21
     pesante
    1.21
     sorella
    1.21
    ፝
    1.20
    ğın
    1.19
    Activations Density 0.034%

    No Known Activations