© 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. 38487
    Prev
    Next
    INDEX
    Explanations

    mapping terrain

    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
     наиболь
    0.50
    habitude
    0.45
    𝒓
    0.45
    érature
    0.43
     вообще
    0.43
    राणिक
    0.40
     effectivement
    0.40
    㛺
    0.40
     perto
    0.40
     පිළිබඳ
    0.40
    POSITIVE LOGITS
    the
    0.51
    zon
    0.48
    dance
    0.48
    um
    0.47
    ita
    0.46
    ui
    0.46
    tech
    0.46
    apo
    0.45
    ITA
    0.45
    ta
    0.45
    Activations Density 0.003%

    No Known Activations