© 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. 34-GEMMASCOPE-RES-131K
    7. 65288
    Prev
    Next
    INDEX
    Explanations

    no or without

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

    The neuron flags tokens expressing negation or absence (e.g. “no,” “not,” “without,” “never”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     radeon
    -1.02
     מאוד
    -1.00
    juga
    -0.98
    nother
    -0.92
     コスプレ
    -0.90
     kgs
    -0.88
    paravant
    -0.87
     exacto
    -0.87
     Reinforcement
    -0.86
     neglecting
    -0.84
    POSITIVE LOGITS
     даже
    2.11
     even
    1.98
    有任何
    1.88
     nawet
    1.84
     any
    1.82
     siquiera
    1.72
    任何
    1.63
     навіть
    1.61
     حتی
    1.59
     slightest
    1.58
    Activations Density 0.057%

    No Known Activations