© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 107257
    Prev
    Next
    INDEX
    Explanations

    post-installation activation

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

    The neuron fires on technical tokens such as numeric literals (e.g. version numbers) and uppercase code identifiers (constants with underscores).

    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
    Categoria
    -0.71
    prz
    -0.68
    MZ
    -0.68
    Номер
    -0.66
     địa
    -0.65
     jednou
    -0.65
     MZ
    -0.65
     雅
    -0.65
    PlayerPrefs
    -0.65
    tabilité
    -0.64
    POSITIVE LOGITS
     лечения
    0.82
    xref
    0.79
    の紹介
    0.78
    ghurt
    0.78
    YM
    0.78
     oras
    0.76
    を変える
    0.75
     Düsseldorf
    0.74
    ductor
    0.74
     vectra
    0.73
    Activations Density 0.004%

    No Known Activations