© 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. 22-GEMMASCOPE-RES-131K
    7. 27837
    Prev
    Next
    INDEX
    Explanations

    places or institutions

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

    The neuron spots prominent single-word topical or domain headings—i.e. the key nouns that label sections or themes.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    E
    -1.55
    q
    -1.45
    H
    -1.27
    A
    -1.26
    T
    -1.24
    k
    -1.23
    p
    -1.21
    u
    -1.21
    is
    -1.16
    n
    -1.16
    POSITIVE LOGITS
     and
    1.55
    estões
    1.16
    ariado
    1.12
    運命
    1.12
    ریان
    1.10
    FINED
    1.10
    daf
    1.09
     kämp
    1.09
    IGNS
    1.09
    uchtigkeit
    1.08
    Activations Density 0.085%

    No Known Activations