© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 1194
    Prev
    Next
    INDEX
    Explanations

    opening or closing delimiters

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

    the opening single or double quote in string literals within code.

    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
     our
    -1.63
    }
    -1.48
     that
    -1.48
    enido
    -1.45
     alliés
    -1.43
     cavallo
    -1.40
    jandra
    -1.38
    轎
    -1.38
     their
    -1.36
     chacun
    -1.35
    POSITIVE LOGITS
    ées
    1.60
    ⬯
    1.52
    om
    1.40
    dimensional
    1.40
    omers
    1.35
     arquitectura
    1.35
    ологи
    1.34
     ज्ञ
    1.34
     getItemCount
    1.34
    hedral
    1.33
    Activations Density 0.033%

    No Known Activations