© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 6073
    Prev
    Next
    INDEX
    Explanations

    inclusive numerical ranges

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Perf
    0.42
     Iglesia
    0.42
     Strada
    0.42
     birinci
    0.40
     Church
    0.39
     Calor
    0.39
     Immaculate
    0.39
    编
    0.39
     iglesia
    0.39
     confesses
    0.39
    POSITIVE LOGITS
     range
    1.13
    範囲
    1.12
    range
    1.02
     ranges
    1.02
     диапа
    0.96
    RANGE
    0.92
    範圍
    0.92
     범위
    0.90
     bounds
    0.89
    Range
    0.86
    Activations Density 0.928%

    No Known Activations