© 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-262K
    7. 7375
    Prev
    Next
    INDEX
    Explanations

    elliptic curves

    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_262k_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
    럿
    0.89
    >**
    0.87
     Pantheon
    0.87
     bridesmaid
    0.84
     chopping
    0.83
    ാൻഡ്
    0.83
    powers
    0.82
     Prohibition
    0.82
    reciation
    0.81
     Outlook
    0.80
    POSITIVE LOGITS
    nmid
    0.91
     skinned
    0.86
     abogados
    0.81
    ipin
    0.79
     blijkt
    0.78
     kriminal
    0.77
    玧
    0.77
    AP
    0.76
    EN
    0.76
     ricerca
    0.76
    Activations Density 0.001%

    No Known Activations