© 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. 170101
    Prev
    Next
    INDEX
    Explanations

    autoencoder, primes, Session, DIY

    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_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
     querying
    0.44
    pady
    0.42
     gerçekten
    0.41
    难
    0.41
    领域的
    0.39
     Senior
    0.39
     struggling
    0.39
     দুঃখ
    0.39
     Leads
    0.39
    ২৯
    0.38
    POSITIVE LOGITS
    ੋ
    0.44
     descriptors
    0.44
     inclinations
    0.44
    𝗢
    0.43
     histograms
    0.42
    ixon
    0.41
                
    0.41
    𝗕
    0.41
    WeakTable
    0.41
     favourites
    0.40
    Activations Density 0.004%

    No Known Activations