© 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. 22-GEMMASCOPE-RES-131K
    7. 128046
    Prev
    Next
    INDEX
    Explanations

    medical or factual outcomes

    np_acts-logits-general · gemini-2.5-flash-lite

    academic or scientific concepts related to research findings, issues, or recommendations.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    wanted
    -1.00
    composed
    -0.91
     chercher
    -0.91
     parcourir
    -0.91
     assister
    -0.90
    辎
    -0.88
     napoli
    -0.88
    verhält
    -0.88
    Wouldn
    -0.87
    覿
    -0.87
    POSITIVE LOGITS
     came
    1.27
     arose
    1.27
     was
    1.20
     arises
    1.19
     is
    1.15
     began
    1.14
     went
    1.13
     comes
    1.07
     may
    1.05
     must
    1.04
    Activations Density 0.196%

    No Known Activations