© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 47577
    Prev
    Next
    INDEX
    Explanations

    if... then.

    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
     Loyal
    0.45
     Pocket
    0.44
     Peninsula
    0.43
     Vanguard
    0.43
    </h3>
    0.43
     Lagoon
    0.42
     Petit
    0.42
     Reservation
    0.42
     Traff
    0.42
     Lago
    0.42
    POSITIVE LOGITS
     učen
    0.49
     femei
    0.49
     vuttam
    0.47
     baš
    0.47
    unat
    0.47
     stvarn
    0.47
     kiểu
    0.46
     wynosi
    0.45
    ഈ
    0.45
    𝚆
    0.45
    Activations Density 0.003%

    No Known Activations