© 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. 92940
    Prev
    Next
    INDEX
    Explanations

    words ending in ent

    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
    Cultura
    -0.88
    igt
    -0.88
    ambiente
    -0.85
    området
    -0.85
    aság
    -0.84
    Einige
    -0.82
    Encrypted
    -0.82
    salt
    -0.82
    holder
    -0.82
    Сан
    -0.81
    POSITIVE LOGITS
    cy
    1.15
    sia
    1.14
    ries
    1.09
    cies
    1.06
    t
    0.88
    ropy
    0.87
    ce
    0.85
    ine
    0.85
    ent
    0.82
    ric
    0.82
    Activations Density 0.119%

    No Known Activations