© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 95472
    Prev
    Next
    INDEX
    Explanations

    method return types

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

    This neuron activates on the return‐type token in method signatures (e.g. the type name like String, int, void, Task, List<…>, Properties, etc.).

    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
    termilk
    -1.18
     meisje
    -1.09
     этих
    -1.07
    ternut
    -1.05
    ㍑
    -1.02
     jeugd
    -1.01
    Auteur
    -1.01
    :「
    -0.99
     garagem
    -0.99
     Questi
    -0.98
    POSITIVE LOGITS
     not
    1.34
     didn
    1.31
     from
    1.22
     across
    1.13
     at
    1.06
     or
    1.03
     about
    1.02
     駅前
    0.99
     of
    0.99
     but
    0.98
    Activations Density 0.002%

    No Known Activations