© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 20524
    Prev
    Next
    INDEX
    Explanations

    authors and works

    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
     explore
    -1.45
     still
    -1.42
     are
    -1.38
    !"
    -1.33
     lomba
    -1.27
     kaca
    -1.27
     what
    -1.26
    ..."
    -1.26
     encontre
    -1.25
     alkoh
    -1.25
    POSITIVE LOGITS
    </th>
    1.37
    1
    1.25
     لهذه
    1.22
     ήταν
    1.21
    läufe
    1.20
     personnels
    1.20
    きり
    1.16
    </td>
    1.16
    Mutability
    1.15
     nunca
    1.13
    Activations Density 0.021%

    No Known Activations