© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 105562
    Prev
    Next
    INDEX
    Explanations

    for me, for you, for us

    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
     on
    -1.70
     where
    -1.50
     is
    -1.43
     '
    -1.24
     tne
    -1.23
    bino
    -1.19
     to
    -1.18
     bedingt
    -1.16
    '
    -1.16
     are
    -1.11
    POSITIVE LOGITS
    憷
    1.41
    espół
    1.40
    Работа
    1.40
    GARET
    1.38
     variedade
    1.38
    鎴
    1.37
    stridium
    1.35
     canaux
    1.35
    kében
    1.34
     thing
    1.34
    Activations Density 0.010%

    No Known Activations