© 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. 31-GEMMASCOPE-2-RES-262K
    7. 53211
    Prev
    Next
    INDEX
    Explanations

    examples or alternatives

    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
     antaranya
    0.46
     Kyi
    0.43
     subjug
    0.41
     chegou
    0.39
    딪
    0.38
     muh
    0.37
     esimerkiksi
    0.37
     dís
    0.37
    चाकी
    0.36
     touchpad
    0.36
    POSITIVE LOGITS
    之类的
    0.55
    或
    0.53
    或其他
    0.53
     अथवा
    0.52
    等
    0.48
     কিংবা
    0.47
    など
    0.45
     অথবা
    0.45
    或者
    0.44
     veya
    0.44
    Activations Density 0.209%

    No Known Activations