© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 75696
    Prev
    Next
    INDEX
    Explanations

    take followed by noun or participle

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     loue
    -1.21
     places
    -1.21
     concept
    -1.19
    clique
    -1.19
    bearded
    -1.13
    骤
    -1.11
     GTX
    -1.09
     fuese
    -1.08
    uft
    -1.07
     simplemente
    -1.07
    POSITIVE LOGITS
     a
    1.91
     också
    1.63
    these
    1.40
    </h5>
    1.38
    żenia
    1.37
    </b>
    1.32
    </i>
    1.31
     Also
    1.27
    ́c
    1.23
    their
    1.20
    Activations Density 0.063%

    No Known Activations