© 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-65K
    7. 707
    Prev
    Next
    INDEX
    Explanations

    action verbs followed by articles

    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_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
    processes
    0.16
    although
    0.14
    }$\
    0.14
    ې
    0.14
     கடு
    0.14
    وڑ
    0.14
     sebagainya
    0.14
    OH
    0.14
     senhores
    0.13
     činn
    0.13
    POSITIVE LOGITS
     the
    0.32
     them
    0.31
     an
    0.28
     one
    0.26
     onto
    0.25
     whichever
    0.25
     a
    0.25
     your
    0.25
     whatever
    0.24
     all
    0.23
    Activations Density 2.695%

    No Known Activations