© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 132574
    Prev
    Next
    INDEX
    Explanations

    with the solar wind

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_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
    ﺿ
    0.46
    ریض
    0.40
     ছই
    0.39
     typu
    0.38
    Multicolored
    0.38
     chicas
    0.38
    }--\
    0.37
    褔
    0.37
     ragazza
    0.37
    nitrogen
    0.36
    POSITIVE LOGITS
     జన
    0.44
     department
    0.43
     fo
    0.40
     Mening
    0.39
     Payroll
    0.38
     తొ
    0.38
    ifique
    0.38
    ampilkan
    0.38
    archa
    0.38
    ounding
    0.38
    Activations Density 0.000%

    No Known Activations