© 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. 22-GEMMASCOPE-RES-131K
    7. 130669
    Prev
    Next
    INDEX
    Explanations

    presentinvention

    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_22/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
    haviours
    -1.10
    tième
    -1.05
    numerusform
    -1.03
    👟
    -1.03
     choose
    -1.02
     '{@
    -1.02
    หลัง
    -1.02
     évé
    -1.01
    ,:),
    -1.00
    pielen
    -0.98
    POSITIVE LOGITS
    大致
    1.05
    了许多
    1.02
    sugges
    0.99
     inmediatamente
    0.96
     delightfully
    0.95
    N
    0.94
     scintill
    0.94
    稍微
    0.94
     somewhat
    0.94
     signif
    0.93
    Activations Density 0.000%

    No Known Activations