© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 77959
    Prev
    Next
    INDEX
    Explanations

    questions about actions in past tense

    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
     flown
    -1.54
     overtaken
    -1.54
     risen
    -1.53
     are
    -1.43
     blown
    -1.42
    thrown
    -1.39
    已经
    -1.37
     spoken
    -1.35
     shaken
    -1.33
     eaten
    -1.31
    POSITIVE LOGITS
     was
    3.42
     did
    3.19
     took
    2.97
     gave
    2.80
     went
    2.59
     drew
    2.44
     didn
    2.36
     saw
    2.33
     became
    2.30
     threw
    2.27
    Activations Density 0.016%

    No Known Activations