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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 9175
    Prev
    Next
    INDEX
    Explanations

    always consistent United

    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_13_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
     prossima
    1.28
    嵘
    1.22
     mejores
    1.21
     delà
    1.16
    越来越
    1.15
     terbesar
    1.14
     maiores
    1.13
     অগ্র
    1.13
    明年
    1.13
     productividad
    1.12
    POSITIVE LOGITS
     commands
    1.13
    cribe
    1.10
    ätt
    1.07
    .
    1.01
     command
    1.00
     commanded
    0.99
     disobey
    0.95
    inspector
    0.95
     separation
    0.94
     labelling
    0.94
    Activations Density 0.000%

    No Known Activations