© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 44696
    Prev
    Next
    INDEX
    Explanations

    skull base

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

    anatomical or structural "base of" something, particularly in medical or technical 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
    畱
    -1.73
     such
    -1.66
     revenir
    -1.60
    \",
    -1.52
     imprescin
    -1.48
    นาด
    -1.45
     hunne
    -1.45
     guangdong
    -1.44
     solcher
    -1.43
     sumptuous
    -1.42
    POSITIVE LOGITS
    𝟮
    1.52
    Even
    1.51
    There
    1.49
     of
    1.45
    Unlike
    1.44
     estilo
    1.41
    كيفية
    1.40
     impacto
    1.38
     Extremely
    1.38
     Generally
    1.38
    Activations Density 0.033%

    No Known Activations