© 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. 41-GEMMASCOPE-2-RES-262K
    7. 94
    Prev
    Next
    INDEX
    Explanations

    criminal charges, agent, packet

    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_all/layer_41_width_262k_l0_big
    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
    <unused973>
    0.64
    ួក
    0.52
    ㇂
    0.50
    <unused984>
    0.47
     ລັບ
    0.46
    <unused2141>
    0.46
    繁忙時間服務
    0.46
    ⺈
    0.46
    ,"%
    0.46
    ᚖ
    0.46
    POSITIVE LOGITS
     Guerra
    0.44
     an
    0.43
     get
    0.43
     Just
    0.42
     Conte
    0.42
    an
    0.42
     Podemos
    0.42
     Expos
    0.42
     Persona
    0.41
     social
    0.40
    Activations Density 0.000%

    No Known Activations