© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 86856
    Prev
    Next
    INDEX
    Explanations

    steps in a process

    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
     Cycle
    -0.75
     Suisse
    -0.74
    mischer
    -0.70
     الان
    -0.69
     Confirm
    -0.69
     کنند
    -0.68
     classifications
    -0.68
     Parameters
    -0.68
     confirming
    -0.68
     Cases
    -0.66
    POSITIVE LOGITS
     step
    0.91
     Hypothe
    0.78
    step
    0.78
    üstung
    0.76
    ۢ
    0.72
    Queued
    0.71
     postoperative
    0.69
     repose
    0.69
     onCreate
    0.67
     angegeben
    0.66
    Activations Density 0.068%

    No Known Activations