© 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. 7-GEMMASCOPE-2-RES-16K
    7. 14465
    Prev
    Next
    INDEX
    Explanations

    claims of infringement

    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_7_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
    ur
    2.29
    د
    2.20
    സ്തു
    2.04
     தெரி
    2.00
     pprint
    2.00
     cít
    1.99
    대표
    1.95
    e
    1.94
    č
    1.87
    decyd
    1.86
    POSITIVE LOGITS
    automated
    2.19
     error
    2.17
     capacitance
    2.13
     centrif
    2.10
    ie
    2.07
     automation
    2.05
     automated
    2.05
    spam
    2.04
     mindless
    1.99
    ారె
    1.99
    Activations Density 0.019%

    No Known Activations