© 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. 53-GEMMASCOPE-2-RES-262K
    7. 8910
    Prev
    Next
    INDEX
    Explanations

    actions and verbs

    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_53_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
     aiding
    0.53
     utilising
    0.48
     desirous
    0.47
     कार्यरत
    0.46
    잦
    0.45
     aids
    0.44
     rostro
    0.44
    惧
    0.44
    하고자
    0.44
     adrift
    0.44
    POSITIVE LOGITS
     buy
    0.73
     put
    0.68
    buy
    0.61
     quit
    0.60
     eat
    0.59
     pretend
    0.58
     drink
    0.55
     donate
    0.55
     bury
    0.55
     sell
    0.54
    Activations Density 0.122%

    No Known Activations