© 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-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 165183
    Prev
    Next
    INDEX
    Explanations

    brain and world model

    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
     estimation
    0.43
     mungkin
    0.41
    τ
    0.40
    ктор
    0.39
     playground
    0.39
     normalizing
    0.39
    Detectable
    0.38
     conectado
    0.38
     daqu
    0.38
    ್
    0.38
    POSITIVE LOGITS
     définitive
    0.44
     seules
    0.43
    decyd
    0.40
     bulldoz
    0.39
     ибо
    0.38
     बहनों
    0.38
     oedd
    0.37
     harmed
    0.36
     ಕೊಡ
    0.36
     Dolls
    0.36
    Activations Density 0.001%

    No Known Activations