© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 81707
    Prev
    Next
    INDEX
    Explanations

    column names or identifiers

    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
     epitom
    -1.24
     for
    -1.22
     on
    -1.19
     unequivocally
    -1.17
     should
    -1.17
     amidst
    -1.16
     profoundly
    -1.13
     ostensibly
    -1.11
     nestled
    -1.10
     undeniably
    -1.10
    POSITIVE LOGITS
    _
    1.46
    particularly
    1.20
    actually
    1.18
    Unnamed
    1.17
     NEW
    1.16
    especially
    1.15
    有些不
    1.12
    really
    1.09
    extremely
    1.09
     voyant
    1.08
    Activations Density 0.044%

    No Known Activations