© 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. 10-GEMMASCOPE-RES-131K
    7. 44898
    Prev
    Next
    INDEX
    Explanations

    termin followed by endings

    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
     of
    -2.47
     We
    -2.47
    我的
    -2.41
     avec
    -2.30
    在他
    -2.28
     The
    -2.27
    他的
    -2.23
    ⡦
    -2.23
    ࿚
    -2.23
     Their
    -2.22
    POSITIVE LOGITS
    梘
    3.02
    the
    2.70
    㐂
    2.45
     plentiful
    2.23
    銲
    2.23
    Ꭳ
    2.19
    覈
    2.17
     coreana
    2.14
    吁
    2.13
     zewnętr
    2.11
    Activations Density 0.005%

    No Known Activations