© 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. 25053
    Prev
    Next
    INDEX
    Explanations

    initiating instructions

    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
     equ
    0.48
     ugu
    0.47
    ه
    0.47
     uygulama
    0.47
     automat
    0.46
     automate
    0.45
     commen
    0.45
     шампу
    0.44
    떤
    0.44
     quod
    0.43
    POSITIVE LOGITS
    ęs
    0.49
     över
    0.49
    iei
    0.48
    ческих
    0.47
    u
    0.46
    ut
    0.46
    isierten
    0.45
    ats
    0.44
    OVER
    0.43
    тым
    0.43
    Activations Density 0.000%

    No Known Activations