© 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. 59107
    Prev
    Next
    INDEX
    Explanations

    matched for age

    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
     borboleta
    -1.45
     wszyscy
    -1.40
     automó
    -1.40
     perfeito
    -1.34
     cuja
    -1.33
    Vä
    -1.32
    …(
    -1.32
     suí
    -1.31
     escolh
    -1.31
     foarte
    -1.31
    POSITIVE LOGITS
     continual
    1.50
     epitom
    1.49
     because
    1.49
     substantially
    1.46
     as
    1.41
     plethora
    1.38
     dazzling
    1.36
     various
    1.36
     longstanding
    1.35
     taking
    1.32
    Activations Density 0.257%

    No Known Activations