© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-65K
    7. 803
    Prev
    Next
    INDEX
    Explanations

    instructions and prompts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    (
    0.96
     (
    0.83
    ](
    0.79
    et
    0.77
    in
    0.74
    </body>
    0.74
    }(
    0.73
    </div>
    0.71
    ![
    0.69
    <h3>
    0.67
    POSITIVE LOGITS
     Veranstaltung
    1.08
     proyecto
    1.07
     ricord
    1.04
     pensamiento
    1.04
    项目
    1.03
    товар
    1.02
    商品
    1.01
    什么是
    1.00
     escenario
    0.98
     pensée
    0.98
    Activations Density 0.103%

    No Known Activations