© 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. 10-GEMMASCOPE-RES-131K
    7. 47
    Prev
    Next
    INDEX
    Explanations

    transcription factor

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

    definitions or explanations in educational or reference content.

    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_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
     ถ้า
    -1.39
    –
    -1.37
    ειτουργ
    -1.18
     عندما
    -1.10
     auguri
    -1.09
    advert
    -1.09
     ſ
    -1.08
    :
    -1.08
    𖤍
    -1.07
    Zdrav
    -1.05
    POSITIVE LOGITS
     that
    2.19
     what
    1.69
     either
    1.48
     others
    1.45
     things
    1.44
     their
    1.26
     verhind
    1.25
     drewni
    1.23
     somebody
    1.23
     anmelden
    1.23
    Activations Density 0.443%

    No Known Activations