© 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. 120260
    Prev
    Next
    INDEX
    Explanations

    takes two arguments

    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
    getattr
    0.42
    Metaxy
    0.41
    ࣪
    0.39
    添加到
    0.38
    ത്തിലേക്ക്
    0.37
    THIRD
    0.37
    فران
    0.36
     وسي
    0.36
    咨
    0.36
    makeConstraints
    0.36
    POSITIVE LOGITS
     two
    0.54
     sebagai
    0.48
     deux
    0.47
     zwei
    0.47
     dois
    0.46
     jako
    0.46
     _
    0.45
     takes
    0.45
     बतौर
    0.45
     seu
    0.45
    Activations Density 0.063%

    No Known Activations