© 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. 4955
    Prev
    Next
    INDEX
    Explanations

    security and system management

    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
    Ger
    0.71
     Ger
    0.70
    ुभ
    0.69
           
    0.67
    GER
    0.67
               
    0.66
     sop
    0.63
     recto
    0.63
    𝐖
    0.63
       
    0.63
    POSITIVE LOGITS
    ↵↵
    0.93
    ionage
    0.91
    ভৌম
    0.85
    }=$
    0.80
     *}
    0.77
    }^{*
    0.76
    幅
    0.74
    yns
    0.73
    ypi
    0.73
    ierungen
    0.72
    Activations Density 0.165%

    No Known Activations