© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 85776
    Prev
    Next
    INDEX
    Explanations

    short periods

    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_10/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
     illustratie
    -1.59
    最初に
    -1.50
    elenco
    -1.45
     moeili
    -1.45
    鮠
    -1.45
    esehen
    -1.44
    ৄ
    -1.41
     dieną
    -1.40
    Forty
    -1.38
     to
    -1.36
    POSITIVE LOGITS
    一旁的
    1.52
    (
    1.45
    在此
    1.35
    i
    1.31
    t
    1.28
     можем
    1.28
    对其
    1.27
    菒
    1.25
    that
    1.23
     pieni
    1.23
    Activations Density 0.017%

    No Known Activations