© 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. 25801
    Prev
    Next
    INDEX
    Explanations

    financial peak or decline

    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
     minimum
    -1.84
     lowest
    -1.80
    最小
    -1.64
    Minimum
    -1.60
     mínimo
    -1.57
    lowest
    -1.56
    最低
    -1.56
    minimum
    -1.55
     Minimum
    -1.48
     lows
    -1.39
    POSITIVE LOGITS
     peaked
    1.41
     peaking
    1.38
    peak
    1.35
     peak
    1.34
     Peak
    1.21
    Peak
    1.13
     peaks
    1.10
     szczy
    1.07
    pea
    1.05
    peaks
    1.04
    Activations Density 0.025%

    No Known Activations