© 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. 22-GEMMASCOPE-RES-131K
    7. 9745
    Prev
    Next
    INDEX
    Explanations

    technical descriptions and medical contexts

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

    words followed by prepositions like "with", "for", "to", or "of" in descriptive text.

    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_22/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
    selbe
    -1.52
    usions
    -1.39
     disponibilités
    -1.35
    fires
    -1.30
    basically
    -1.29
     uur
    -1.25
     lii
    -1.22
    蚰
    -1.22
     attente
    -1.22
    mely
    -1.22
    POSITIVE LOGITS
     marvellous
    1.58
     stupendous
    1.56
     Because
    1.48
     extraordinarily
    1.44
     innumerable
    1.43
    9
    1.41
     unquestionably
    1.40
    未必
    1.40
     unbelievable
    1.37
     disconcer
    1.37
    Activations Density 0.207%

    No Known Activations