© 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. 119139
    Prev
    Next
    INDEX
    Explanations

    treatment response

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

    Russian language text content with high activations for Cyrillic characters.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    hlen
    -0.69
    getline
    -0.69
    Kill
    -0.68
    ါ
    -0.68
     cil
    -0.67
    kni
    -0.66
    tetra
    -0.66
     Quill
    -0.65
     bewegen
    -0.65
    Purpose
    -0.64
    POSITIVE LOGITS
    gement
    0.74
     entourage
    0.73
    まるで
    0.71
    نجليزية
    0.69
     внимания
    0.69
     beruf
    0.69
    Dunk
    0.68
    polated
    0.67
    concatenate
    0.66
    )))),
    0.66
    Activations Density 0.042%

    No Known Activations