© 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. 40436
    Prev
    Next
    INDEX
    Explanations

    loading model or data

    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
    ዃ
    0.45
    does
    0.44
    vocabulary
    0.42
    гли
    0.42
    end
    0.42
    batch
    0.41
     अगेन
    0.41
    縮
    0.41
    also
    0.41
     nhận
    0.40
    POSITIVE LOGITS
    كتوبر
    0.45
    拒
    0.43
     لمدة
    0.42
     Tempor
    0.42
     Anwendungen
    0.42
     Bürger
    0.42
     irreparable
    0.41
     nightmare
    0.41
     பெருமா
    0.41
     EPL
    0.41
    Activations Density 0.002%

    No Known Activations