© 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. 40246
    Prev
    Next
    INDEX
    Explanations

    appropriate tool for harmful content

    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
     particularly
    0.39
    ,
    0.37
     besonders
    0.37
     particolarmente
    0.36
     also
    0.36
     vigorously
    0.35
     particularmente
    0.35
     merely
    0.35
     added
    0.35
     বিশেষ
    0.35
    POSITIVE LOGITS
    に関する法律
    0.47
     เขา
    0.40
    ந
    0.39
    ष्णु
    0.38
    宦
    0.38
    꾼
    0.37
    ަ
    0.37
    ᚄ
    0.37
    Ɲ
    0.37
    
    0.37
    Activations Density 0.078%

    No Known Activations