© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 43824
    Prev
    Next
    INDEX
    Explanations

    mane, LDL cholesterol

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

    medical and biochemical terms, especially LDL (low-density lipoprotein) and pony anatomy terms like "mane".

    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
    鏵
    -2.55
    ਃ
    -2.23
     konkrete
    -2.22
    〼
    -2.20
    geſ
    -2.16
    “
    -2.11
    antaranya
    -2.08
    ////////
    -2.08
    ⁆
    -2.08
     If
    -2.06
    POSITIVE LOGITS
    m
    3.11
    身影
    2.44
    the
    2.41
    il
    2.34
    B
    2.33
     marvels
    2.25
     остается
    2.20
    F
    2.17
     approximating
    2.13
    x
    2.11
    Activations Density 0.010%

    No Known Activations