© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 34813
    Prev
    Next
    INDEX
    Explanations

    end of sentence or clause

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

    The neuron flags subjective evaluations and emphatic, opinionated statements—i.e. phrases that express value judgments or strong appraisals.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     themselves
    -0.96
    பெ
    -0.96
    ni
    -0.96
    那种
    -0.96
    няют
    -0.94
     fossa
    -0.94
     thier
    -0.94
    those
    -0.93
    iz
    -0.92
    Thats
    -0.91
    POSITIVE LOGITS
     it
    2.19
    它
    1.31
    它的
    1.21
     It
    1.16
    
    1.15
     它
    1.09
     we
    1.06
     you
    1.04
    它是
    1.04
     anything
    1.03
    Activations Density 0.075%

    No Known Activations