© 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. 99758
    Prev
    Next
    INDEX
    Explanations

    organization tied to

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

    The neuron is highly sensitive to longer content words (tokens with four or more characters), regardless of part of speech.

    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
    BUYER
    -0.88
    scribers
    -0.78
    ிய
    -0.77
    erweise
    -0.76
     referred
    -0.74
    śli
    -0.72
     enige
    -0.72
    Funciones
    -0.72
    夸
    -0.71
     dẫn
    -0.71
    POSITIVE LOGITS
     phone
    1.32
     telephone
    1.03
    Phone
    0.98
     Phone
    0.94
     following
    0.91
    phone
    0.90
     этого
    0.89
     erhältlich
    0.87
    anema
    0.87
    msgTypes
    0.84
    Activations Density 0.001%

    No Known Activations