© 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. 128071
    Prev
    Next
    INDEX
    Explanations

    quilt, LGBTQ, cleanser, transporter, absorbance, acidity, Quaternion

    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
    and
    -3.02
    酲
    -2.67
    「
    -2.66
    ции
    -2.56
    ኧ
    -2.44
    While
    -2.33
    了他
    -2.31
    ”,
    -2.31
    ing
    -2.30
    or
    -2.28
    POSITIVE LOGITS
    autogui
    3.14
     skvě
    2.38
     wichtigste
    2.34
    ſſi
    2.28
    pAd
    2.27
     but
    2.27
    ↵
    2.27
     сказал
    2.23
    UGHTER
    2.19
     velmi
    2.19
    Activations Density 0.012%

    No Known Activations