© 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. 112463
    Prev
    Next
    INDEX
    Explanations

    cut out

    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
    ين
    0.58
    ંભ
    0.57
     बनने
    0.50
    踺
    0.49
    ेल
    0.48
    వేయ
    0.46
    ൈ
    0.46
     मित्त
    0.45
    échange
    0.44
    𝒂
    0.43
    POSITIVE LOGITS
     magnetism
    0.49
     aqueous
    0.47
     Indigenous
    0.46
     atrop
    0.45
     kudos
    0.45
     ATO
    0.45
     relational
    0.45
     dogma
    0.44
     adenosine
    0.44
     Marxism
    0.43
    Activations Density 0.004%

    No Known Activations