© 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. 73885
    Prev
    Next
    INDEX
    Explanations

    liquefaction and faction

    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
    テスト
    -0.74
     pantai
    -0.71
     bioavailability
    -0.69
    urlaub
    -0.67
    线
    -0.66
     stain
    -0.65
    ingham
    -0.64
     træ
    -0.63
    یکر
    -0.63
     SUSTAIN
    -0.63
    POSITIVE LOGITS
    faction
    1.44
     liquef
    1.44
     Liqu
    1.05
     liqu
    1.04
    fac
    0.94
     faction
    0.90
     rar
    0.84
    Fac
    0.83
    fraction
    0.81
    ification
    0.79
    Activations Density 0.075%

    No Known Activations