© 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. 40-GEMMASCOPE-2-RES-262K
    4. 109160
    Prev
    Next
    INDEX
    Explanations

    stars fallen, that detects, a temporary

    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_40_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
     sticks
    0.45
     c
    0.43
     ฝ
    0.41
     stick
    0.40
     prou
    0.39
     này
    0.38
     personally
    0.38
     hội
    0.38
     ค
    0.37
     Gund
    0.37
    POSITIVE LOGITS
    procedure
    0.41
    看法
    0.41
    ختلف
    0.40
    eniu
    0.39
    鼓勵
    0.39
    들에
    0.39
    DEBUGFS
    0.39
     होम्योपै
    0.38
    ρευ
    0.38
    mostat
    0.38
    Activations Density 0.000%

    No Known Activations