© 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. 112013
    Prev
    Next
    INDEX
    Explanations

    benefits and policy timelines

    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
     contratar
    0.46
     afgelopen
    0.44
    uerung
    0.42
     gick
    0.41
    腦
    0.41
    喜剧
    0.40
    綏
    0.39
    ᅣ
    0.39
     utilisé
    0.39
    хозяй
    0.39
    POSITIVE LOGITS
     cognit
    0.39
     necessariamente
    0.39
     nécessairement
    0.38
    टाम
    0.37
    bracketing
    0.37
     sooner
    0.36
     may
    0.36
     submer
    0.36
     subset
    0.35
     featuring
    0.35
    Activations Density 0.016%

    No Known Activations