© 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. 72293
    Prev
    Next
    INDEX
    Explanations

    extreme high or low levels

    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
     or
    -1.63
     and
    -1.43
    álise
    -1.39
     which
    -1.30
    絃
    -1.25
     Pandit
    -1.24
    ємо
    -1.22
     жовтня
    -1.21
     GetEnumerator
    -1.20
    AuthService
    -1.20
    POSITIVE LOGITS
     огром
    1.71
     amounts
    1.44
     altes
    1.41
     neue
    1.35
     словно
    1.28
     буквально
    1.28
     adored
    1.27
    !
    1.27
    \\
    1.26
     Ut
    1.25
    Activations Density 0.081%

    No Known Activations