© 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. 73857
    Prev
    Next
    INDEX
    Explanations

    comparing with different

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

    This neuron detects in-text scholarly reference markers and cross-reference cues (e.g. “cf.,” “compare,” numerical citations).

    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
    絝
    -1.68
    </h5>
    -1.59
    chrift
    -1.51
     toate
    -1.38
    </h1>
    -1.38
    Either
    -1.37
     We
    -1.37
     LOOK
    -1.36
    </b>
    -1.35
    mozilla
    -1.34
    POSITIVE LOGITS
     with
    1.65
     their
    1.55
     different
    1.53
     one
    1.51
     our
    1.47
     Celebr
    1.38
     being
    1.37
     encourages
    1.30
     those
    1.30
    采用了
    1.28
    Activations Density 0.006%

    No Known Activations