© 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-65K
    7. 53031
    Prev
    Next
    INDEX
    Explanations

    numbers followed by punctuation

    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_65k_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
    睽
    0.41
     Melon
    0.38
     chin
    0.38
    umac
    0.38
     Meld
    0.37
    厙
    0.37
     Alber
    0.37
    chin
    0.37
    در
    0.36
    SHA
    0.36
    POSITIVE LOGITS
    的时
    0.46
    ীষ্ম
    0.43
    ،
    0.42
    。
    0.41
    .…
    0.41
    खरी
    0.41
     pourrez
    0.40
    ofSeconds
    0.40
     kategorii
    0.40
     सक्छ
    0.40
    Activations Density 0.001%

    No Known Activations