© 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. 1416
    Prev
    Next
    INDEX
    Explanations

    {to, value, duration, message}

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

    The neuron strongly activates on numeric literal tokens (integer constants) in the code.

    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
     would
    -1.01
     various
    -0.81
     solidly
    -0.81
     Sharks
    -0.81
     highly
    -0.81
    要不然
    -0.79
     forthcoming
    -0.78
    棻
    -0.77
    engaruhi
    -0.77
     just
    -0.76
    POSITIVE LOGITS
     AMONG
    1.06
    _:
    1.05
     "":
    0.97
     '':
    0.93
    cripts
    0.89
     dû
    0.89
     ANNOUNC
    0.87
     };
    0.85
     ngan
    0.85
     GETS
    0.84
    Activations Density 0.016%

    No Known Activations