© 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-65K
    7. 48833
    Prev
    Next
    INDEX
    Explanations

    prep time and cook time minutes

    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_31_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
    Price
    0.42
    Cooldown
    0.41
    نمية
    0.40
    においても
    0.39
     downloader
    0.39
    cite
    0.39
    Prices
    0.38
    炉
    0.38
    网页
    0.38
     imputation
    0.38
    POSITIVE LOGITS
     revisions
    0.46
     acept
    0.45
     revise
    0.44
     candidat
    0.43
     Sachen
    0.43
     revision
    0.43
     revised
    0.42
     candidats
    0.42
     aprov
    0.42
     revising
    0.42
    Activations Density 0.005%

    No Known Activations