© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 112677
    Prev
    Next
    INDEX
    Explanations

    `@2x` filename or `KEY_ROWIDLL`

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

    string concatenation operators in programming code, particularly the plus sign used to join strings or build expressions.

    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
     ήταν
    -1.41
    зывали
    -1.34
     版
    -1.34
     abandonné
    -1.29
     hormigón
    -1.27
     tỏi
    -1.27
     cinto
    -1.26
    eadas
    -1.25
     июня
    -1.23
     oublié
    -1.23
    POSITIVE LOGITS
    8
    1.88
    2
    1.62
    7
    1.59
    5
    1.59
    6
    1.57
     and
    1.48
    9
    1.48
    all
    1.47
    4
    1.47
     anymore
    1.43
    Activations Density 0.002%

    No Known Activations