© 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. 74568
    Prev
    Next
    INDEX
    Explanations

    Arch bishop, diocese, street, Linux, archivist

    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
     It
    -3.33
    艄
    -2.98
    )
    -2.63
    缡
    -2.61
    鹩
    -2.41
    ⩴
    -2.27
     що
    -2.20
    袮
    -2.16
     said
    -2.16
     ternyata
    -2.14
    POSITIVE LOGITS
    3
    2.89
    𖥦
    2.59
    č
    2.58
     szczeg
    2.55
     intolerable
    2.44
     retten
    2.39
    许多
    2.38
     unambiguous
    2.34
     положения
    2.34
    }$
    2.34
    Activations Density 0.012%

    No Known Activations