© 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. 108779
    Prev
    Next
    INDEX
    Explanations

    descriptive states or actions

    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
     denn
    0.46
     ਸ
    0.44
     innen
    0.44
     vermek
    0.43
     orice
    0.43
    єю
    0.42
     jedem
    0.42
     Diput
    0.42
     misinterpreted
    0.42
     छात्र
    0.41
    POSITIVE LOGITS
     Aeronaut
    0.47
    ט
    0.47
    ون
    0.46
    >.
    0.45
    ID
    0.44
    ']
    0.44
    ').
    0.43
    ag
    0.43
    ня
    0.42
    𝗣
    0.41
    Activations Density 0.000%

    No Known Activations