© 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. 47729
    Prev
    Next
    INDEX
    Explanations

    giving and receiving

    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
     &
    -1.11
     and
    -1.04
    呸
    -0.99
    nościo
    -0.96
    thing
    -0.92
    substring
    -0.88
    も同じ
    -0.88
    すみません
    -0.87
    /
    -0.87
    </h3>
    -0.86
    POSITIVE LOGITS
    ॄ
    1.16
     when
    1.14
     regarding
    1.14
    ἵ
    1.11
    discussions
    1.11
     évé
    1.10
    ppled
    1.10
     while
    1.05
    icted
    1.02
    см
    1.02
    Activations Density 0.075%

    No Known Activations