© 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. 89746
    Prev
    Next
    INDEX
    Explanations

    pitch

    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
    ステップ
    -0.88
     =
    -0.86
     cutting
    -0.81
     typically
    -0.80
    従
    -0.80
    マウス
    -0.79
    I
    -0.76
    Ответ
    -0.75
     nonetheless
    -0.73
     nevertheless
    -0.73
    POSITIVE LOGITS
     pitch
    2.17
    Pitch
    2.13
    pitch
    2.08
     Pitch
    2.05
    fork
    1.82
     pitches
    1.66
     pitching
    1.60
    forks
    1.58
    blende
    1.48
    pitched
    1.35
    Activations Density 0.006%

    No Known Activations