© 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. 113166
    Prev
    Next
    INDEX
    Explanations

    narrative characters or concepts

    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
     ঘনত্ব
    0.46
     பிரபலமான
    0.46
     పదార్థ
    0.46
     \%$,
    0.46
     அற்புதமான
    0.46
    韌
    0.45
     crypto
    0.45
     મુખ્ય
    0.45
     ソ
    0.44
     במ
    0.44
    POSITIVE LOGITS
     etter
    0.48
     efter
    0.45
     suits
    0.45
     Entsche
    0.42
    ссер
    0.42
     purpose
    0.41
     целью
    0.41
    َح
    0.41
     whose
    0.40
     teacher
    0.40
    Activations Density 0.006%

    No Known Activations