© 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. 4107
    Prev
    Next
    INDEX
    Explanations

    code identifiers and punctuation

    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
    wins
    -0.82
    スピード
    -0.71
    の前
    -0.66
     month
    -0.65
    ="#"><
    -0.65
     speed
    -0.65
     собра
    -0.64
     warts
    -0.64
    bezpiec
    -0.63
     Model
    -0.63
    POSITIVE LOGITS
    lova
    0.79
    Kalau
    0.74
    PEER
    0.73
    leggio
    0.72
     ferm
    0.72
    ท่าน
    0.69
     octo
    0.68
    莽
    0.67
    ΕΣ
    0.66
    Romance
    0.66
    Activations Density 0.064%

    No Known Activations