© 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. 194172
    Prev
    Next
    INDEX
    Explanations

    History, innovation, holidays, moving, night, state, skills

    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
     nat
    0.47
    슷
    0.44
     کیشن
    0.44
     pili
    0.40
    埒
    0.40
     plutôt
    0.38
     jár
    0.38
     যুগ্ম
    0.38
    ބ
    0.38
    𝕝
    0.38
    POSITIVE LOGITS
     never
    0.98
     Never
    0.87
    Never
    0.85
     nunca
    0.81
    never
    0.79
     никогда
    0.77
     NEVER
    0.75
     nigdy
    0.73
    从未
    0.73
    Nunca
    0.70
    Activations Density 0.029%

    No Known Activations