© 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. 102866
    Prev
    Next
    INDEX
    Explanations

    introducing a premise or context

    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
     it
    -1.26
     hauptsächlich
    -1.14
     meistens
    -1.10
     you
    -1.06
     Definitely
    -1.05
    iramente
    -1.05
    pochette
    -1.02
    踴
    -0.97
    siapkan
    -0.97
    zość
    -0.96
    POSITIVE LOGITS
     the
    3.53
     how
    2.20
     our
    1.45
     efforts
    1.24
     attempts
    1.12
    arım
    1.10
    Sự
    1.09
    tiéndose
    1.07
     what
    1.07
    berapa
    1.05
    Activations Density 0.139%

    No Known Activations