© 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
    2. Gemma-3-270M-IT
    3. 12-GEMMASCOPE-2-RES-65K
    4. 1019
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_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
     deceased
    1.02
    鬍
    0.86
    lass
    0.84
     comisión
    0.83
    テナンス
    0.82
    以為
    0.81
     درمان
    0.78
     eliminación
    0.77
    akhir
    0.77
    瀝
    0.77
    POSITIVE LOGITS
    Newton
    1.38
     Newton
    1.28
     Karak
    1.25
     narr
    1.24
     Yin
    1.22
     primal
    1.16
     Bret
    1.16
    _+
    1.16
    analog
    1.15
     quadr
    1.14
    Activations Density 0.732%

    No Known Activations