© 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. 65523
    Prev
    Next
    INDEX
    Explanations

    actual empirical

    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
    alló
    -0.99
    jenige
    -0.90
    ềm
    -0.89
    izarse
    -0.85
     popularidad
    -0.85
    encial
    -0.84
    BASEPATH
    -0.84
     oll
    -0.83
     essenti
    -0.82
    兩
    -0.82
    POSITIVE LOGITS
     actual
    1.79
     actually
    1.45
     truly
    1.42
     tatsächlich
    1.13
     fully
    1.13
     true
    1.13
     formal
    1.12
     Actually
    1.11
    真正的
    1.08
     Actual
    1.05
    Activations Density 0.126%

    No Known Activations