© 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. 111172
    Prev
    Next
    INDEX
    Explanations

    numbers and acronyms

    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
    ᄍ
    0.44
     near
    0.42
     heirs
    0.39
     fe
    0.39
     weekday
    0.38
     equals
    0.37
     sober
    0.37
     ba
    0.37
     concur
    0.37
    近く
    0.37
    POSITIVE LOGITS
    ۀ
    0.41
    テープ
    0.39
    Tape
    0.38
    খ্য
    0.38
    PART
    0.38
    须知
    0.38
    Spawner
    0.37
     рэгістрацыі
    0.37
     ப்ளாக்
    0.37
    Freq
    0.37
    Activations Density 0.005%

    No Known Activations