© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 97656
    Prev
    Next
    INDEX
    Explanations

    figuring out your adventure

    np_acts-logits-general · gemini-2.5-flash-lite

    contrasting or describing phenomena

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aturally
    0.47
     及び
    0.47
     ブル
    0.46
    年
    0.46
     男女
    0.46
    ple
    0.45
     cf
    0.44
     लग्न
    0.44
    plt
    0.43
     灬
    0.43
    POSITIVE LOGITS
    लाम
    0.51
     vetor
    0.46
     inoxydable
    0.45
    hate
    0.45
    钓
    0.44
     collectibles
    0.42
    saturation
    0.42
    Tecla
    0.42
     poblaciones
    0.42
    ][:
    0.42
    Activations Density 0.000%

    No Known Activations