© 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. 22-GEMMASCOPE-RES-131K
    4. 36017
    Prev
    Next
    INDEX
    Explanations

    A comparison of findings

    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
     teknis
    -1.49
     krach
    -1.32
     tatuajes
    -1.30
    鲧
    -1.27
     visse
    -1.27
     คา
    -1.23
     Februari
    -1.21
     🥰
    -1.21
     interieur
    -1.20
     appartement
    -1.20
    POSITIVE LOGITS
     how
    1.65
     a
    1.63
     an
    1.59
     especially
    1.53
     two
    1.51
     use
    1.48
     including
    1.46
     particularly
    1.43
     insbesondere
    1.41
     results
    1.37
    Activations Density 0.121%

    No Known Activations