© 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. 223112
    Prev
    Next
    INDEX
    Explanations

    connecting concepts

    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
    那
    0.47
    getResult
    0.42
    果
    0.42
     unlucky
    0.40
     secretly
    0.39
    】
    0.39
     aquela
    0.38
     이유는
    0.38
    最后
    0.38
     작
    0.38
    POSITIVE LOGITS
     Meanwhile
    0.59
     Through
    0.56
     meanwhile
    0.53
    Meanwhile
    0.52
     Durch
    0.51
    通過
    0.51
    Durch
    0.51
    我們可以
    0.49
    ளாக
    0.49
    ளிலும்
    0.48
    Activations Density 0.004%

    No Known Activations