© 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. 19687
    Prev
    Next
    INDEX
    Explanations

    molecular, acute, chronic, fake, beam, electronic, liquid, dialog, micro, insert, pH

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

    scientific and technical terms in academic or professional contexts.

    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
     their
    -1.35
     –
    -1.28
    Their
    -1.27
    asties
    -1.22
     їх
    -1.21
     ὁ
    -1.20
     Their
    -1.17
     их
    -1.17
     «
    -1.16
     Schauspielerin
    -1.16
    POSITIVE LOGITS
     նաև
    1.32
     it
    1.29
     剑
    1.25
    CÓ
    1.21
     myös
    1.20
     viciss
    1.19
    Szer
    1.17
     ausdrücklich
    1.17
     अन्य
    1.16
     racconta
    1.16
    Activations Density 0.335%

    No Known Activations