© 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. 1886
    Prev
    Next
    INDEX
    Explanations

    study buddy or partner

    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
    ところ
    0.91
    植
    0.86
    ఊ
    0.83
    moved
    0.82
     હતું
    0.79
    of
    0.79
    detailed
    0.79
    奶油
    0.78
     అని
    0.78
    ر
    0.78
    POSITIVE LOGITS
     partner
    0.95
     vendo
    0.88
     compañero
    0.87
     companion
    0.85
     Rizal
    0.84
     therefore
    0.82
     partenaire
    0.81
     consequently
    0.80
     buddy
    0.80
     comrade
    0.76
    Activations Density 0.000%

    No Known Activations