© 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. 14916
    Prev
    Next
    INDEX
    Explanations

    prenatal diagnosis and care

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

    names of people and medical/scientific terms.

    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
    \
    -3.03
    to
    -2.84
    ti
    -2.72
    ).
    -2.44
    餮
    -2.39
     achieve
    -2.38
    و
    -2.38
    にします
    -2.28
    as
    -2.23
    ce
    -2.23
    POSITIVE LOGITS
    
    2.94
     podéis
    2.55
    नलोड
    2.44
    迓
    2.33
    0
    2.30
    Ⴈ
    2.27
     که
    2.19
    푣
    2.16
    砣
    2.16
    ܊
    2.14
    Activations Density 0.026%

    No Known Activations