© 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. 32250
    Prev
    Next
    INDEX
    Explanations

    Indian Institutes or international entities

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

    The neuron responds to multi‐letter uppercase sequences (acronyms/initialisms) such as IIS, IIT, II, and similar all‐caps tokens.

    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
    utusan
    -0.82
    cisme
    -0.79
    angerie
    -0.78
    ጺ
    -0.77
    衩
    -0.77
    ownerId
    -0.76
     июня
    -0.75
     steuer
    -0.75
    naphthal
    -0.75
     recursively
    -0.74
    POSITIVE LOGITS
     how
    0.81
    饞
    0.69
    vt
    0.66
     assistir
    0.65
     ii
    0.65
    Caught
    0.65
     darin
    0.64
     пред
    0.64
     plantel
    0.64
     HOW
    0.63
    Activations Density 0.017%

    No Known Activations