© 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. 34-GEMMASCOPE-RES-131K
    7. 4292
    Prev
    Next
    INDEX
    Explanations

    code snippets or programming 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_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
     including
    -1.11
     from
    -0.99
     what
    -0.96
     giving
    -0.96
    árt
    -0.95
     all
    -0.94
     just
    -0.94
     Many
    -0.94
     with
    -0.93
     Some
    -0.93
    POSITIVE LOGITS
     delightfully
    1.08
     incess
    1.04
     reiterated
    1.00
     exceedingly
    0.99
     explic
    0.99
     wonderfully
    0.99
     impo
    0.98
     delightful
    0.95
     semelh
    0.93
     disgruntled
    0.93
    Activations Density 0.000%

    No Known Activations