© 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-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 9419
    Prev
    Next
    INDEX
    Explanations

    engine failures and malfunctions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_22_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ()
    1.03
    can
    0.92
    jor
    0.90
     (
    0.88
     Can
    0.87
     када
    0.87
     (--
    0.87
     பின்
    0.85
    ว้
    0.83
    (
    0.83
    POSITIVE LOGITS
     certainly
    2.21
     perhaps
    2.11
     indeed
    2.05
    indeed
    1.96
     certes
    1.94
     doubtless
    1.88
     definitely
    1.87
     surely
    1.87
     quizás
    1.85
     certamente
    1.84
    Activations Density 0.265%

    No Known Activations