© 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. 58326
    Prev
    Next
    INDEX
    Explanations

    noun phrases and compound words

    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
    aluminium
    -1.02
     stabilis
    -0.84
     Organisations
    -0.80
     aluminium
    -0.80
    rises
    -0.79
     STUDIO
    -0.79
     Organis
    -0.77
    localisation
    -0.77
    ऑ
    -0.76
    рики
    -0.75
    POSITIVE LOGITS
     Qi
    0.85
     Motion
    0.84
    MOTION
    0.84
    ModelAndView
    0.79
    intah
    0.78
    drav
    0.76
     الرحمن
    0.76
    婢
    0.76
    想的
    0.74
     Los
    0.74
    Activations Density 0.057%

    No Known Activations