© 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. 7040
    Prev
    Next
    INDEX
    Explanations

    to + action verb

    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
    💿
    -0.90
    🚽
    -0.87
    ᶫ
    -0.87
    🖇
    -0.84
     stá
    -0.84
     pneus
    -0.82
    📀
    -0.82
    Posté
    -0.79
    perty
    -0.79
     optimieren
    -0.79
    POSITIVE LOGITS
     capture
    2.66
    capture
    2.14
    Capture
    2.11
     Capture
    2.08
     capturing
    2.08
     tap
    1.97
     captured
    1.94
     captures
    1.89
     tapping
    1.88
    Capt
    1.69
    Activations Density 0.046%

    No Known Activations