© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 113153
    Prev
    Next
    INDEX
    Explanations

    angular.module

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

    opening single quotation marks in JavaScript/programming code, particularly after function calls like `module(` or `controller(`.

    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
    }
    -3.03
    </h3>
    -2.80
     neues
    -2.34
     of
    -2.22
    
    -2.19
    s
    -2.17
     ähn
    -2.08
    
    -2.03
    ก็
    -2.02
    
    -2.02
    POSITIVE LOGITS
    栳
    2.58
    ”？
    2.44
     These
    2.31
    梣
    2.27
    彣
    2.20
    各样的
    2.17
    м
    2.17
    鋨
    2.16
    كرت
    2.14
    (
    2.14
    Activations Density 0.019%

    No Known Activations