© 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. 65151
    Prev
    Next
    INDEX
    Explanations

    is necessary to

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

    The neuron detects expressions of necessity or obligation—phrases that tell you something “is necessary,” “must,” “need to,” or “can’t” do 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
     isn
    -1.60
     can
    -1.51
    佧
    -1.48
     todavía
    -1.40
     didn
    -1.39
     в
    -1.39
    っき
    -1.38
     bygget
    -1.38
     följande
    -1.35
     expliqué
    -1.35
    POSITIVE LOGITS
     ............
    1.48
    ...');
    1.43
    asjons
    1.40
    瓒
    1.38
    años
    1.36
    ...");
    
    1.34
    tft
    1.33
     殼
    1.31
    ...]
    1.30
    ...";
    1.30
    Activations Density 0.010%

    No Known Activations