© 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. 116700
    Prev
    Next
    INDEX
    Explanations

    free software licenses

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    𝗅
    -0.76
    european
    -0.72
     Rasen
    -0.71
    vga
    -0.69
    tft
    -0.69
     Farina
    -0.68
     soucis
    -0.67
     Cleo
    -0.66
    oat
    -0.66
    Населення
    -0.66
    POSITIVE LOGITS
    ofire
    0.81
    ɔ
    0.74
    ја
    0.71
    康
    0.71
    diagnostics
    0.69
    שׁ
    0.67
    ฉ
    0.67
    —
    0.67
    Da
    0.66
    tima
    0.66
    Activations Density 0.041%

    No Known Activations