© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 49783
    Prev
    Next
    INDEX
    Explanations

    character case conversion

    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
    ]>=
    -0.82
    STM
    -0.80
     wnios
    -0.77
     Monday
    -0.76
     possibility
    -0.73
     you
    -0.73
    rcs
    -0.72
    $",
    -0.72
    গ্র
    -0.72
     supplies
    -0.72
    POSITIVE LOGITS
    DISE
    0.79
    museum
    0.79
    련
    0.77
    Kag
    0.75
    遺跡
    0.74
    ობ
    0.73
    зик
    0.73
    第七
    0.72
     زرد
    0.72
     אינו
    0.72
    Activations Density 0.008%

    No Known Activations