© 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. 107032
    Prev
    Next
    INDEX
    Explanations

    license and provided

    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
     PCC
    -0.80
     armes
    -0.73
     genommen
    -0.73
    ын
    -0.72
     СП
    -0.71
     leiden
    -0.71
    gehende
    -0.71
     flot
    -0.71
     incongru
    -0.69
    abba
    -0.69
    POSITIVE LOGITS
     pondering
    0.85
    Причины
    0.70
    Espagne
    0.70
     would
    0.69
    ühle
    0.69
     within
    0.69
     другу
    0.68
    キッド
    0.68
     ausgesprochen
    0.68
     mysterious
    0.67
    Activations Density 0.156%

    No Known Activations