© 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. 16-GEMMASCOPE-2-RES-262K
    7. 20020
    Prev
    Next
    INDEX
    Explanations

    natural functions and expressions

    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_16_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
    s
    0.62
    Aren
    0.54
    Tour
    0.53
    SG
    0.52
    קל
    0.52
    1
    0.52
    at
    0.52
     (
    0.50
    str
    0.50
    Town
    0.50
    POSITIVE LOGITS
    섦
    0.58
     lichaam
    0.50
     nipples
    0.50
     subside
    0.50
     leaflet
    0.48
     vestib
    0.48
     вста
    0.48
    નિક
    0.48
     câ
    0.48
     nipple
    0.47
    Activations Density 0.000%

    No Known Activations