© 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. 33376
    Prev
    Next
    INDEX
    Explanations

    as if; in spite of; although

    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
    -1.41
    inspira
    -1.29
    Scorpio
    -1.27
    Sagittarius
    -1.24
    鼕
    -1.23
    Pener
    -1.20
    Mika
    -1.18
    ÍN
    -1.14
    뺀
    -1.11
    asaran
    -1.10
    POSITIVE LOGITS
     []:
    1.31
    we
    1.26
    </h2>
    1.26
    also
    1.24
     they
    1.24
    ¯
    1.21
    ®
    1.21
    */
    1.18
    it
    1.14
     we
    1.12
    Activations Density 0.055%

    No Known Activations