© 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. 34-GEMMASCOPE-RES-131K
    7. 31506
    Prev
    Next
    INDEX
    Explanations

    everyone being or doing something

    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_34/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
     also
    -1.39
     अन्य
    -1.16
     أخرى
    -1.09
     másik
    -1.09
     سایر
    -1.07
     другие
    -1.03
     भी
    -1.00
     many
    -1.00
     other
    -1.00
    ทั้งหมด
    -0.98
    POSITIVE LOGITS
     одина
    1.77
     except
    1.55
     their
    1.45
     Everyone
    1.45
     alike
    1.40
     including
    1.39
    Everyone
    1.31
     agree
    1.31
    except
    1.30
     Agree
    1.28
    Activations Density 0.049%

    No Known Activations