© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 90392
    Prev
    Next
    INDEX
    Explanations

    joc, toc, hoc, boc

    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
     Having
    -0.90
    Having
    -0.83
    ꯀ
    -0.75
     παρου
    -0.72
    زان
    -0.71
    Translation
    -0.71
     Knowing
    -0.70
    ásra
    -0.69
    lumb
    -0.69
    Passcode
    -0.69
    POSITIVE LOGITS
    tober
    1.03
    oc
    0.85
    uman
    0.84
     hoc
    0.84
     noc
    0.81
    tehende
    0.81
    loc
    0.75
    boc
    0.74
     Mocha
    0.74
    umen
    0.73
    Activations Density 0.065%

    No Known Activations