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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 4018
    Prev
    Next
    INDEX
    Explanations

    Key improvements and explanations

    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
    詎
    0.31
     exploiting
    0.30
     anyways
    0.30
    磪
    0.30
     anyway
    0.29
     constat
    0.29
    休日
    0.29
     montré
    0.29
    违反
    0.28
     niezb
    0.28
    POSITIVE LOGITS
    Several
    0.41
    Important
    0.40
     Important
    0.39
    Tips
    0.37
    Here
    0.37
     importante
    0.37
     Notes
    0.37
     Here
    0.37
    几
    0.37
    ----------------
    0.36
    Activations Density 0.008%

    No Known Activations