© 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. 67454
    Prev
    Next
    INDEX
    Explanations

    academic, research, or institutional terms

    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
     of
    -2.19
     or
    -1.56
    </b>
    -1.53
    )
    -1.45
    ),
    -1.38
     effort
    -1.37
    },
    -1.35
    หรือ
    -1.27
    ”
    -1.25
     warum
    -1.22
    POSITIVE LOGITS
    ByIndex
    1.38
    bierz
    1.34
     gents
    1.29
    辔
    1.23
     even
    1.20
     by
    1.19
     позволяют
    1.18
    Украина
    1.18
     telinga
    1.18
    ING
    1.17
    Activations Density 0.453%

    No Known Activations