© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 36678
    Prev
    Next
    INDEX
    Explanations

    simple freelance

    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
    은
    0.51
    을
    0.50
    ing
    0.46
    ة
    0.42
    构
    0.42
    ள
    0.41
    ée
    0.41
    े
    0.41
    })
    0.41
    估
    0.41
    POSITIVE LOGITS
     heartache
    0.53
     জরিমানা
    0.52
     mortgages
    0.48
     तकलीफ
    0.48
    നിക്ക്
    0.47
     refunds
    0.47
     acela
    0.46
     cheques
    0.45
     Oké
    0.45
     sakte
    0.45
    Activations Density 0.011%

    No Known Activations