© 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. 48912
    Prev
    Next
    INDEX
    Explanations

    create, help, notice, observed

    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
     Elabor
    0.47
     जॉर्ज
    0.47
    ご
    0.46
     Multimedia
    0.46
     Afrika
    0.46
    ປະ
    0.45
    تحان
    0.45
    聃
    0.45
    전
    0.45
     práctico
    0.44
    POSITIVE LOGITS
     definitively
    0.46
    odes
    0.45
    Absent
    0.45
     joyous
    0.43
    ancien
    0.42
     purposefully
    0.42
    uds
    0.41
    oulders
    0.41
     consistently
    0.40
     гря
    0.40
    Activations Density 0.002%

    No Known Activations