© 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. 53-GEMMASCOPE-2-RES-262K
    7. 9291
    Prev
    Next
    INDEX
    Explanations

    ascending, descending, condescending

    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_53_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
    शिलाजीत
    0.45
     ഉപ
    0.40
     sockaddr
    0.40
     liệt
    0.39
    噘
    0.39
     thải
    0.39
     thật
    0.38
    ቁ
    0.38
    followlike
    0.38
    ঃখ
    0.37
    POSITIVE LOGITS
     ascending
    1.34
     ascend
    1.34
     descend
    1.33
     ascended
    1.30
     descending
    1.28
     Asc
    1.26
    ending
    1.25
     descended
    1.23
    Asc
    1.22
    ascending
    1.18
    Activations Density 0.021%

    No Known Activations