© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 10947
    Prev
    Next
    INDEX
    Explanations

    cpp, java, php, go, js, c++ includes

    np_acts-logits-general · gemini-2.5-flash-lite

    method or function calls on objects in code, particularly when accessing properties or invoking methods using dot notation.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
    -2.20
     with
    -1.41
     The
    -1.38
     on
    -1.30
     importantly
    -1.28
     offering
    -1.25
     ofere
    -1.24
     uncovered
    -1.21
     the
    -1.15
    blusa
    -1.15
    POSITIVE LOGITS
     only
    1.56
     januari
    1.55
    .*")]
    1.47
     élas
    1.46
    asthan
    1.44
    áctica
    1.42
     februari
    1.40
    uteurs
    1.39
     chansons
    1.38
     mostrarse
    1.38
    Activations Density 0.052%

    No Known Activations