© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 47955
    Prev
    Next
    INDEX
    Explanations

    **/**

    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
     ملك
    0.51
    ເອ
    0.49
     ය
    0.45
     النف
    0.44
     कंस
    0.44
     Wer
    0.43
     संदर्भ
    0.42
     പ്രധാന
    0.42
     ပြ
    0.42
     땅
    0.42
    POSITIVE LOGITS
     immersing
    0.41
    Param
    0.40
     constantly
    0.39
     wavelengths
    0.39
    不管
    0.39
    SSF
    0.38
    Gaussian
    0.38
    Viol
    0.38
     প্রতিক্রি
    0.37
    sqrt
    0.37
    Activations Density 0.004%

    No Known Activations