© 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. 48766
    Prev
    Next
    INDEX
    Explanations

    explaining possibilities or conditions

    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
     unangemessene
    -1.41
     диамет
    -1.20
    ныя
    -1.19
     kürzlich
    -1.18
    Valley
    -1.17
    gradable
    -1.15
     generaciones
    -1.15
     вашей
    -1.14
     bénéficier
    -1.13
     unangemess
    -1.13
    POSITIVE LOGITS
     there
    2.28
     it
    2.19
     also
    1.81
     this
    1.77
     nowadays
    1.63
     in
    1.59
     sometimes
    1.49
     they
    1.46
     probably
    1.44
     usually
    1.42
    Activations Density 0.254%

    No Known Activations