© 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. 35046
    Prev
    Next
    INDEX
    Explanations

    initialization and context

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

    This neuron activates on identifiers of function or method calls (names immediately followed by “(”).

    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
     our
    -1.13
     their
    -1.10
    ΤΟ
    -1.05
     its
    -1.05
    cobacterium
    -1.04
    psin
    -1.03
    ℕ
    -1.03
    tidine
    -1.02
     ANY
    -1.02
     who
    -1.02
    POSITIVE LOGITS
    suitable
    1.21
    ✴
    1.09
     réfrig
    1.08
    Dota
    1.08
    Instal
    1.05
    Forza
    1.04
    SIST
    1.04
    Cia
    1.02
    REGIONAL
    1.02
    TERR
    1.02
    Activations Density 0.032%

    No Known Activations