© 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. 116755
    Prev
    Next
    INDEX
    Explanations

    values between ranges

    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
    mathrm
    -1.09
    шее
    -1.02
    setcounter
    -0.98
     years
    -0.98
     ".";
    -0.97
     场
    -0.92
     what
    -0.92
     isn
    -0.90
     \%$
    -0.88
    റ്
    -0.88
    POSITIVE LOGITS
     sebesar
    1.02
    werte
    1.02
     pourront
    0.99
     Спи
    0.98
     réfrig
    0.98
    kategori
    0.96
     étan
    0.96
     itemprop
    0.96
     welkom
    0.96
     $
    0.94
    Activations Density 0.162%

    No Known Activations