© 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. 60760
    Prev
    Next
    INDEX
    Explanations

    code delimiters and terminators

    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
    梣
    -1.45
    ︲
    -1.39
    _
    -1.32
     Apalagi
    -1.26
     обратиться
    -1.21
     воспользоваться
    -1.21
    tifying
    -1.20
    parseLong
    -1.16
     allowed
    -1.15
    
    -1.15
    POSITIVE LOGITS
     but
    1.81
     tetapi
    1.77
     as
    1.65
     namun
    1.52
    ↵
    1.52
    ]$.
    1.45
    他现在
    1.41
     jotka
    1.38
     Frankrijk
    1.37
    )։
    1.37
    Activations Density 0.014%

    No Known Activations