© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 109104
    Prev
    Next
    INDEX
    Explanations

    shader effects

    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
     Bax
    -0.89
     density
    -0.81
    MODE
    -0.76
    筮
    -0.76
    Baca
    -0.75
     potra
    -0.74
    JRadioButton
    -0.73
     BAR
    -0.73
    惰
    -0.72
    BAR
    -0.71
    POSITIVE LOGITS
     effect
    1.10
    effect
    0.96
    Effect
    0.92
     techniques
    0.89
     technique
    0.89
     effects
    0.85
     Effect
    0.84
     HL
    0.84
     FX
    0.82
     Techniques
    0.81
    Activations Density 0.051%

    No Known Activations