© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 125965
    Prev
    Next
    INDEX
    Explanations

    actions or potential for

    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
     মহাশয়
    0.47
    вис
    0.43
    ISPW
    0.42
    璎
    0.41
     namen
    0.41
     لیں
    0.40
     چکا
    0.40
     başlad
    0.40
     দিবেন
    0.40
    <0xBF>
    0.40
    POSITIVE LOGITS
     Entfer
    0.46
    orate
    0.45
    ophe
    0.44
     terroir
    0.43
    liess
    0.42
     damal
    0.41
    vors
    0.41
     Divide
    0.40
     Octopus
    0.40
     Consid
    0.40
    Activations Density 0.003%

    No Known Activations