© 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-262K
    7. 13294
    Prev
    Next
    INDEX
    Explanations

    comparison operators

    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
    ските
    0.49
    ówki
    0.46
    த்தைத்
    0.46
    ():
    0.46
    芾
    0.45
    சை
    0.44
    бя
    0.43
    ড
    0.43
    מי
    0.42
    unstyled
    0.42
    POSITIVE LOGITS
     zus
    0.56
     than
    0.48
     limo
    0.48
     sowohl
    0.47
    OrEqualTo
    0.46
     nin
    0.46
     kuin
    0.46
    istische
    0.45
     train
    0.45
     mouthful
    0.45
    Activations Density 0.045%

    No Known Activations