© 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. 93707
    Prev
    Next
    INDEX
    Explanations

    sorry

    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
     iii
    0.48
    Despite
    0.46
    ränkt
    0.44
     “[
    0.44
     چند
    0.43
     вскоре
    0.42
     خاصة
    0.42
     depois
    0.41
    之後
    0.40
     ব্যক্ত
    0.40
    POSITIVE LOGITS
     screwdriver
    0.52
     colesterol
    0.49
     ഭക്ഷണ
    0.46
    ITIONAL
    0.45
    ্ের
    0.44
    MON
    0.43
     dishwasher
    0.42
     ा
    0.42
    arle
    0.41
    icrosoft
    0.41
    Activations Density 0.001%

    No Known Activations