© 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. 22-GEMMASCOPE-RES-131K
    7. 72172
    Prev
    Next
    INDEX
    Explanations

    preposition or verb followed by pronoun

    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
     and
    -1.65
     of
    -1.58
     for
    -1.40
    imothy
    -1.37
     ratusan
    -1.30
     seluruh
    -1.30
    mitsub
    -1.27
     sejumlah
    -1.26
     pembaca
    -1.24
     keseluruhan
    -1.23
    POSITIVE LOGITS
     Buah
    1.26
     メニュー
    1.24
     it
    1.22
     finne
    1.22
     tager
    1.21
     cuivre
    1.19
    masing
    1.19
     vack
    1.16
    HostException
    1.13
    رنگ
    1.12
    Activations Density 0.052%

    No Known Activations