© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 989
    Prev
    Next
    INDEX
    Explanations

    watch for, watch this, watch the, watch live

    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
    }
    -1.70
    </h4>
    -1.59
     sigue
    -1.48
    )
    -1.47
     }
    -1.45
     và
    -1.45
    xaml
    -1.39
    lenen
    -1.39
    ítez
    -1.38
    侂
    -1.35
    POSITIVE LOGITS
     the
    1.83
     グリル
    1.43
     how
    1.41
    +),
    1.41
    :@
    1.38
    รวจ
    1.33
    ilaku
    1.29
    </i>
    1.29
    *),
    1.27
     sparen
    1.27
    Activations Density 0.011%

    No Known Activations