© 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. 10-GEMMASCOPE-RES-131K
    7. 101102
    Prev
    Next
    INDEX
    Explanations

    into difficult situations

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

    The neuron detects forceful, dynamic “verb + into” constructions (e.g. plunges into, thrust into, slides into) that describe sudden immersion or movement into something.

    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
    棪
    -1.88
    亊
    -1.88
    驒
    -1.72
    年後
    -1.70
     ceramica
    -1.66
    怍
    -1.60
     户
    -1.58
     dibanding
    -1.56
    使用方法
    -1.55
    ギュラー
    -1.55
    POSITIVE LOGITS
     into
    1.38
    难以
    1.36
     ........
    1.30
    ,
    1.29
     cette
    1.28
      
    1.26
     in
    1.26
    沦
    1.23
     Diese
    1.23
     
    1.23
    Activations Density 0.026%

    No Known Activations