© 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. 31528
    Prev
    Next
    INDEX
    Explanations

    states, appeals, email addresses

    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
    ندية
    -0.75
     revisions
    -0.75
     reactions
    -0.72
    следова
    -0.72
    ganj
    -0.71
     yourselves
    -0.71
     responses
    -0.70
    ฟัง
    -0.69
    [][
    -0.69
     oint
    -0.69
    POSITIVE LOGITS
     passés
    0.91
    sad
    0.77
    續
    0.77
     perdon
    0.75
     cuán
    0.74
     ruido
    0.74
     如
    0.73
    说了
    0.72
     clínicos
    0.72
     malheureusement
    0.71
    Activations Density 0.028%

    No Known Activations