© 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. 2546
    Prev
    Next
    INDEX
    Explanations

    Hidden Markov Model

    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
     està
    -0.81
    分类
    -0.75
    argento
    -0.75
     mysqli
    -0.73
     Mule
    -0.73
    ISHI
    -0.72
     McBride
    -0.71
    ĩnh
    -0.70
    weihnachts
    -0.70
     classification
    -0.69
    POSITIVE LOGITS
     HMM
    1.33
    Emissions
    1.27
     Viter
    1.23
     Emissions
    1.20
     emissions
    1.15
     emission
    1.15
    HMM
    1.13
    emissions
    1.13
     Emission
    1.09
    hmm
    1.05
    Activations Density 0.009%

    No Known Activations