© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 9257
    Prev
    Next
    INDEX
    Explanations

    comparative phrases

    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_65k_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
    <unused13>
    0.39
    <unused56>
    0.39
     njegove
    0.39
     chở
    0.38
     nhất
    0.38
     builders
    0.38
     candlestick
    0.38
     moguće
    0.38
     cómo
    0.37
     cumplimiento
    0.37
    POSITIVE LOGITS
    raints
    0.50
    Tail
    0.46
    Turn
    0.43
    Due
    0.43
    У
    0.43
    Ε
    0.42
    U
    0.41
    É
    0.41
    Line
    0.40
    UP
    0.39
    Activations Density 0.095%

    No Known Activations