© 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. 40-GEMMASCOPE-2-RES-262K
    7. 31635
    Prev
    Next
    INDEX
    Explanations

    flutter bloc, form, blue, gallery

    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
    榊
    0.43
    Node
    0.40
    Tara
    0.40
     Tara
    0.38
    Vu
    0.37
    paras
    0.36
     Jullie
    0.36
    “.
    0.36
    Paras
    0.36
     разби
    0.36
    POSITIVE LOGITS
    ᕕ
    0.42
     sicher
    0.39
     efficacement
    0.39
     sigur
    0.39
    ⤠
    0.38
     вывод
    0.37
    erder
    0.37
     einiger
    0.36
    业内
    0.36
     absch
    0.36
    Activations Density 0.000%

    No Known Activations