© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 73426
    Prev
    Next
    INDEX
    Explanations

    the view of

    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
    ),
    -2.80
     they
    -2.25
    ”,
    -2.06
    ).
    -2.00
    ”
    -1.99
    x
    -1.98
    \
    -1.92
    the
    -1.91
     is
    -1.88
    up
    -1.87
    POSITIVE LOGITS
    盉
    2.09
    敺
    2.03
     the
    1.98
    žas
    1.88
     iſt
    1.87
    ਗ਼
    1.86
     花纹
    1.85
    甃
    1.85
    dass
    1.84
    
    1.83
    Activations Density 0.006%

    No Known Activations