© 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. 17-GEMMASCOPE-2-RES-16K
    7. 1814
    Prev
    Next
    INDEX
    Explanations

    SAMHSA National Helpline

    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_17_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
     bodyParser
    1.38
    tabPadding
    1.29
     <!--<
    1.25
     //@
    1.25
    nok
    1.25
         
    1.24
    hatiti
    1.23
     सूफ़ी
    1.23
     Сасик
    1.22
    彠
    1.22
    POSITIVE LOGITS
    ↵
    1.35
    ↵↵↵
    1.03
    </strong>
    1.02
     coming
    1.00
     dienen
    0.96
     duty
    0.95
     equival
    0.94
     Coming
    0.92
     equal
    0.91
     clar
    0.90
    Activations Density 0.013%

    No Known Activations