© 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. 34-GEMMASCOPE-RES-131K
    4. 60454
    Prev
    Next
    INDEX
    Explanations

    associated with

    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
     delightfully
    -1.13
     dezelfde
    -1.11
    莇
    -1.10
     wonderfully
    -1.09
     exceedingly
    -1.09
     secluded
    -1.06
     tranquil
    -1.04
     tumultuous
    -1.03
     praticamente
    -1.02
     strikingly
    -1.01
    POSITIVE LOGITS
     with
    1.70
    Usually
    1.23
    Various
    1.20
    Typically
    1.17
     JUST
    1.16
     various
    1.16
    Numerous
    1.13
     activities
    1.11
     ONLY
    1.11
    Two
    1.10
    Activations Density 0.050%

    No Known Activations