© 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. 33036
    Prev
    Next
    INDEX
    Explanations

    entity states or actions

    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
    Médaille
    -1.41
     nzuri
    -1.30
    にします
    -1.28
    場合には
    -1.14
    を目指す
    -1.10
    bringt
    -1.09
     gebeten
    -1.09
    に挑戦
    -1.09
     muhimu
    -1.08
    zaamheid
    -1.08
    POSITIVE LOGITS
     is
    2.50
     was
    2.25
     largely
    1.42
     occurred
    1.40
     wasn
    1.32
    を
    1.32
    があり
    1.30
     isn
    1.30
    ですが
    1.27
     has
    1.27
    Activations Density 0.181%

    No Known Activations