© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 45185
    Prev
    Next
    INDEX
    Explanations

    strategic vision

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

    The neuron strongly activates on descriptive adjectives (including demonyms and participial/-ic/-ian-type adjectives).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    <td>
    -1.59
     &
    -1.38
     =='
    -1.37
    })+
    -1.37
    isies
    -1.37
    瀟
    -1.36
     والإ
    -1.35
    ꦲ
    -1.34
    nastics
    -1.34
    })}$
    -1.31
    POSITIVE LOGITS
     the
    1.84
     kaufen
    1.54
     that
    1.50
    充分
    1.48
     bestellen
    1.45
     how
    1.38
    [
    1.37
     anúncios
    1.32
     ermöglicht
    1.30
    眎
    1.30
    Activations Density 0.720%

    No Known Activations