© 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. 53994
    Prev
    Next
    INDEX
    Explanations

    iteration over range

    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
     episodes
    -0.89
    ℃
    -0.88
     never
    -0.84
     ning
    -0.83
    ゜
    -0.82
    ệm
    -0.78
    BRA
    -0.76
     thut
    -0.76
     Kø
    -0.75
    伯
    -0.75
    POSITIVE LOGITS
     range
    2.02
    range
    1.48
    Range
    1.20
     Range
    1.10
     RANGE
    1.05
     ranges
    1.02
     :=
    0.98
    RANGE
    0.97
     ranging
    0.92
     диапа
    0.85
    Activations Density 0.009%

    No Known Activations