© 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. 107725
    Prev
    Next
    INDEX
    Explanations

    questions or "Q:" followed by text

    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
     this
    -0.91
    كيف
    -0.82
     when
    -0.81
     revital
    -0.79
    因此
    -0.79
     forty
    -0.77
    িখ
    -0.76
     it
    -0.75
     all
    -0.75
     supposedly
    -0.75
    POSITIVE LOGITS
    alternative
    0.89
    NAF
    0.84
    Pico
    0.83
     POSSIBLE
    0.82
    Possible
    0.82
     જ
    0.82
     bied
    0.81
    puede
    0.81
    POSSIBLE
    0.80
    GameMode
    0.80
    Activations Density 0.002%

    No Known Activations