© 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. 40047
    Prev
    Next
    INDEX
    Explanations

    programming context or specific identifiers

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

    This neuron detects occurrences of “inflate” and “Inflater” (e.g. LayoutInflater, MenuInflater, getLayoutInflater) in Android code.

    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
     to
    -1.32
    훗
    -1.31
     their
    -1.24
    大声
    -1.14
    .*;
    -1.13
    providedIn
    -1.13
     become
    -1.12
    ࿚
    -1.11
     como
    -1.09
    anguardia
    -1.09
    POSITIVE LOGITS
     côtes
    1.22
    gebruik
    1.16
     chevron
    1.16
     expla
    1.15
     assis
    1.14
     можешь
    1.14
     availa
    1.13
     gorges
    1.13
    Manif
    1.12
     leaft
    1.12
    Activations Density 0.001%

    No Known Activations