© 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. 31-GEMMASCOPE-2-RES-262K
    7. 52976
    Prev
    Next
    INDEX
    Explanations

    Category and goal descriptions

    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_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
     tribulations
    0.47
    overlay
    0.46
    piry
    0.46
    rov
    0.44
     descript
    0.44
     redact
    0.44
     descriptive
    0.43
    }});
    0.43
     fluv
    0.42
    linen
    0.42
    POSITIVE LOGITS
    如下
    0.49
    伍
    0.46
    本セット
    0.45
    此
    0.45
    %，
    0.44
    芯片
    0.43
     Rename
    0.42
    包
    0.42
     Championships
    0.41
     Schools
    0.40
    Activations Density 0.001%

    No Known Activations