© 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. 62785
    Prev
    Next
    INDEX
    Explanations

    alarm activation or event

    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
     Kome
    -0.90
    amphetamine
    -0.79
    seed
    -0.79
    ynne
    -0.79
    veg
    -0.74
     SEED
    -0.73
     fouls
    -0.72
     Automated
    -0.71
     comet
    -0.71
    impôt
    -0.71
    POSITIVE LOGITS
     went
    1.55
     goes
    1.43
     off
    1.26
     Going
    1.25
     going
    1.24
    Going
    1.20
    鳴
    1.19
     go
    1.08
    Goes
    0.95
     sounded
    0.95
    Activations Density 0.018%

    No Known Activations