© 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. 33823
    Prev
    Next
    INDEX
    Explanations

    appear to be or seem

    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
     attempted
    -1.06
     attempt
    -1.02
    try
    -1.01
     tried
    -1.00
     also
    -0.92
    orithmic
    -0.91
    ால்
    -0.89
    óa
    -0.88
     حاول
    -0.88
     already
    -0.84
    POSITIVE LOGITS
     seemingly
    1.77
     seeming
    1.77
    seem
    1.55
     seem
    1.55
    看似
    1.41
     aparente
    1.34
     Seem
    1.32
     aparentemente
    1.28
     apparente
    1.26
     apparent
    1.21
    Activations Density 0.131%

    No Known Activations