© 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. 102900
    Prev
    Next
    INDEX
    Explanations

    syllable + consonant/vowel ending

    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
    벤트
    -0.76
    eak
    -0.75
    amic
    -0.74
    rendering
    -0.73
    radas
    -0.73
     Sugges
    -0.72
     haunting
    -0.72
    ijų
    -0.71
    winding
    -0.71
     Kenney
    -0.70
    POSITIVE LOGITS
    QUIRY
    0.82
     szer
    0.74
     Common
    0.73
     sustains
    0.72
    srcs
    0.72
     sau
    0.70
    冪
    0.70
    춧
    0.70
     jde
    0.69
     sustain
    0.69
    Activations Density 0.031%

    No Known Activations