© 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. 40505
    Prev
    Next
    INDEX
    Explanations

    natural and architectural landscapes

    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
     Masalah
    -2.34
     Beberapa
    -2.19
    اخته
    -2.16
     Memper
    -2.11
     Sekarang
    -2.11
     Siehe
    -2.09
     Tujuan
    -2.09
    .")
    -2.08
     Mungkin
    -2.08
     UNIVERSIT
    -2.06
    POSITIVE LOGITS
    (
    3.16
    b
    2.84
    i
    2.69
    e
    2.63
    O
    2.44
    f
    2.34
     alleged
    2.28
    R
    2.23
    L
    2.19
    Z
    2.17
    Activations Density 0.007%

    No Known Activations