© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 4133
    Prev
    Next
    INDEX
    Explanations

    largest or ranked entities

    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_34/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
     that
    -1.08
     to
    -1.05
     particularly
    -1.03
     including
    -1.03
     especially
    -0.93
     Global
    -0.89
     from
    -0.88
     incluido
    -0.87
    ="
    -0.87
     [`
    -0.86
    POSITIVE LOGITS
     by
    2.47
    measured
    1.99
     measured
    1.81
     Measured
    1.72
    Measured
    1.69
     according
    1.40
     based
    1.38
     MEASURE
    1.36
    terms
    1.31
     with
    1.30
    Activations Density 0.098%

    No Known Activations