© 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. 10-GEMMASCOPE-RES-131K
    7. 1854
    Prev
    Next
    INDEX
    Explanations

    administrating, administrated, administrating, matriarch, periodontitis, perioperative, idiopathic, idiomatically

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

    medical or technical terms with prefixes like "idio-", "perio-", and "matri-".

    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
    ’
    -2.92
     It
    -2.44
     was
    -2.41
     ‘
    -2.33
     
    -2.30
    ichtete
    -2.27
    н
    -2.25
     &
    -2.20
     ’
    -2.19
    人在
    -2.14
    POSITIVE LOGITS
    )$
    3.25
    e
    3.16
    </h3>
    2.97
    }$
    2.75
     {
    2.69
     休闲
    2.59
     漂亮
    2.59
    ayaquil
    2.53
    man
    2.48
    """
    2.48
    Activations Density 0.036%

    No Known Activations