Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 8201
    Prev
    Next
    INDEX
    Explanations

    hyaluronic acid

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

    chemical or technical terms containing "al", "yal", "ural", or similar letter combinations.

    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
    less
    -1.45
    ია
    -1.33
    lv
    -1.16
    land
    -1.15
    landschaft
    -1.12
    lf
    -1.11
    länge
    -1.09
    ో
    -1.09
    lines
    -1.09
    ln
    -1.09
    POSITIVE LOGITS
    led
    1.30
    ton
    1.28
    istically
    1.21
    lic
    1.13
    iser
    1.02
    lography
    1.02
    dehyde
    1.00
    lia
    0.98
    istic
    0.98
    r
    0.97
    Activations Density 0.692%

    No Known Activations