© 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. 500
    Prev
    Next
    INDEX
    Explanations

    need to adverbs

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    )}=\
    1.80
    piry
    1.79
     Brides
    1.75
    }}=$
    1.74
     Arrows
    1.71
    }}=(
    1.70
    }}=\
    1.68
    }|=
    1.68
    ungg
    1.68
     Entries
    1.67
    POSITIVE LOGITS
     intently
    1.35
     באופן
    1.29
     openly
    1.28
     спокойно
    1.28
    7
    1.25
    8
    1.24
     autonomously
    1.24
    3
    1.21
     свободно
    1.19
     silently
    1.17
    Activations Density 1.073%

    No Known Activations