© 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. 65325
    Prev
    Next
    INDEX
    Explanations

    unaware of the truth

    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
     seemed
    -0.91
     لهذا
    -0.90
     scheint
    -0.90
     ولا
    -0.88
     Theories
    -0.86
     Primitive
    -0.86
     accusation
    -0.84
    似乎
    -0.84
    Tb
    -0.82
     dette
    -0.82
    POSITIVE LOGITS
     hidden
    1.76
     secretly
    1.63
     unknowingly
    1.43
     concealed
    1.42
    hidden
    1.41
     Hidden
    1.28
    Hidden
    1.27
     secret
    1.26
     Unbe
    1.19
    HIDDEN
    1.19
    Activations Density 0.041%

    No Known Activations