© 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. 3270
    Prev
    Next
    INDEX
    Explanations

    words ending in ll

    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
    ive
    -0.85
    ain
    -0.82
    ado
    -0.79
    ྱི་
    -0.77
    ize
    -0.76
    д
    -0.76
    iv
    -0.75
    imagen
    -0.74
    ify
    -0.73
     faked
    -0.73
    POSITIVE LOGITS
    ington
    1.13
    ture
    1.13
    llll
    0.97
    ard
    0.97
    isions
    0.96
    🍿
    0.96
    treatment
    0.94
     sinon
    0.91
    tative
    0.90
    inger
    0.90
    Activations Density 0.080%

    No Known Activations