© 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. 31-GEMMASCOPE-2-RES-262K
    7. 3126
    Prev
    Next
    INDEX
    Explanations

    helps when needed

    np_acts-logits-general · gemini-2.5-flash-lite

    tokens describing concrete actions and outcomes in a medical procedure or clinical incident report.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_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
     unsurprisingly
    0.57
     преимущественно
    0.56
     забезпе
    0.51
     பெரும்பாலான
    0.51
     अद्वितीय
    0.51
     alongside
    0.50
     inescap
    0.50
    {\
    0.50
     crucially
    0.48
     brimming
    0.48
    POSITIVE LOGITS
     THEM
    0.50
     them
    0.48
     rtn
    0.48
     γιατί
    0.47
     acolo
    0.46
     nieve
    0.46
     vajj
    0.45
    them
    0.44
     hubby
    0.44
     naman
    0.44
    Activations Density 0.111%

    No Known Activations