© 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. 34-GEMMASCOPE-RES-131K
    4. 70283
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     on
    -1.25
     even
    -1.12
     all
    -1.10
     what
    -1.06
     highly
    -1.05
     that
    -1.03
     their
    -1.03
     entirely
    -1.01
     at
    -1.00
     has
    -1.00
    POSITIVE LOGITS
    </i>
    1.16
     カットソー
    1.13
    </em>
    1.09
    providing
    0.97
    拄
    0.93
    ute
    0.91
     topl
    0.91
     expli
    0.91
    </s>
    0.89
     spezi
    0.89
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.