© 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. 34-GEMMASCOPE-RES-131K
    7. 55744
    Prev
    Next
    INDEX
    Explanations

    programming code blocks

    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
    umos
    -0.73
    conceito
    -0.71
     Experienced
    -0.68
     turb
    -0.67
    equiv
    -0.66
    Identify
    -0.66
    maro
    -0.66
     zoveel
    -0.65
     オブ
    -0.65
    CLOS
    -0.65
    POSITIVE LOGITS
     строй
    0.70
    istat
    0.69
    ὦ
    0.69
    fone
    0.69
    存于互联网档案馆
    0.68
    crackers
    0.67
    縫
    0.66
     doPost
    0.65
    eavor
    0.65
    itects
    0.64
    Activations Density 0.039%

    No Known Activations