© 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
    2. Gemma-3-1B
    3. 17-GEMMASCOPE-2-RES-16K
    4. 1874
    Prev
    Next
    INDEX
    Explanations

    listing types or examples

    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
    】.
    0.90
    }).
    0.87
    *.
    0.84
    }.
    0.83
    *}
    0.82
    ❤️
    0.81
    });
    0.81
    !.
    0.80
     });
    0.78
    </h2>
    0.75
    POSITIVE LOGITS
     menyiapkan
    1.20
     menyediakan
    1.18
    给了
    1.16
     ฉาก
    1.14
     เอา
    1.13
     спеціа
    1.11
     nogle
    1.11
     những
    1.11
     jakieś
    1.10
    を用意
    1.10
    Activations Density 0.352%

    No Known Activations