© 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. 6658
    Prev
    Next
    INDEX
    Explanations

    actions followed by prepositions

    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
     badass
    0.64
    Awesome
    0.59
     idk
    0.58
     freaking
    0.56
     俺
    0.55
    awesome
    0.55
    yeah
    0.51
     roommate
    0.50
    咻
    0.50
     kiddos
    0.49
    POSITIVE LOGITS
     envisaged
    0.71
     pensioners
    0.66
     enquiries
    0.64
     marvellous
    0.64
     convivial
    0.59
     maths
    0.58
     sociable
    0.58
     carers
    0.56
     adverts
    0.56
     watercolour
    0.56
    Activations Density 0.002%

    No Known Activations