© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 62918
    Prev
    Next
    INDEX
    Explanations

    program execution information

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

    The neuron responds to numeric tokens or number‐like strings (e.g. standalone digits, measurements, years, file versions).

    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
     Simón
    -0.74
     jutaan
    -0.72
    ☬
    -0.70
     SIMON
    -0.67
     thoughtful
    -0.67
     professional
    -0.65
     wszyscy
    -0.64
     Пі
    -0.64
     વા
    -0.64
     semaine
    -0.63
    POSITIVE LOGITS
     Einblick
    0.68
     nieces
    0.67
     شکل
    0.66
    SqlSession
    0.65
    psycho
    0.65
     Opens
    0.63
     kneeling
    0.63
     penyebab
    0.63
    Psycho
    0.62
     dług
    0.62
    Activations Density 0.065%

    No Known Activations