© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 67952
    Prev
    Next
    INDEX
    Explanations

    robbery and bankruptcy

    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
    ar
    -3.03
    ?"
    -3.02
    er
    -2.83
     was
    -2.81
    utched
    -2.66
    埽
    -2.59
    甃
    -2.56
    琑
    -2.52
    is
    -2.39
    or
    -2.38
    POSITIVE LOGITS
    ↵
    4.28
    ↵↵
    3.33
    ).
    3.02
     vollständ
    2.94
    .
    2.81
    anyahu
    2.45
    屜
    2.33
     zwölf
    2.28
     gewöhnlich
    2.28
     andererseits
    2.27
    Activations Density 0.027%

    No Known Activations