© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 31356
    Prev
    Next
    INDEX
    Explanations

    great promise or quality

    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
     крупные
    -0.92
    大型
    -0.83
     Fähigkeit
    -0.82
     крупных
    -0.78
     широкий
    -0.77
    ンピース
    -0.74
    ยาว
    -0.74
    ద్
    -0.74
    alah
    -0.74
    command
    -0.73
    POSITIVE LOGITS
     great
    3.33
     tremendous
    3.09
     considerable
    2.97
     immense
    2.83
    considerable
    2.48
     greater
    2.34
    great
    2.31
     much
    2.25
     enormous
    2.17
     greatest
    2.13
    Activations Density 0.116%

    No Known Activations