© 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. 73377
    Prev
    Next
    INDEX
    Explanations

    comparative phrasing

    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
    -1.37
    轳
    -1.26
    IT
    -1.22
    และ
    -1.19
     海报
    -1.14
    Ն
    -1.11
     и
    -1.08
     or
    -1.07
     bygge
    -1.07
    鎘
    -1.06
    POSITIVE LOGITS
     It
    1.88
     The
    1.61
     they
    1.59
     than
    1.51
     Würde
    1.41
    cios
    1.36
     Its
    1.34
     pubblicazione
    1.33
    仅仅
    1.33
     Both
    1.26
    Activations Density 0.022%

    No Known Activations