© 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. 103534
    Prev
    Next
    INDEX
    Explanations

    You can/may/should/might

    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
     your
    -1.62
     you
    -1.38
     ask
    -1.16
     remove
    -1.14
     make
    -1.11
     which
    -1.08
     is
    -1.07
     its
    -1.06
     jesu
    -1.05
     when
    -1.05
    POSITIVE LOGITS
    might
    1.19
    なども
    1.18
     protože
    1.15
    XIII
    1.13
    could
    1.13
    ‟
    1.13
     pasting
    1.11
     ailing
    1.10
    XII
    1.08
    XVII
    1.06
    Activations Density 0.047%

    No Known Activations