© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 23617
    Prev
    Next
    INDEX
    Explanations

    code explanations and technical terms

    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
    ләр
    0.49
    ៤
    0.48
    Соцмережа
    0.47
    𒌓
    0.45
     वाढ
    0.45
    ലെസ്
    0.45
    <unused348>
    0.45
     вас
    0.44
     demands
    0.43
    SRPC
    0.43
    POSITIVE LOGITS
    پ
    0.48
    know
    0.42
    ្នាំ
    0.41
    Italia
    0.41
    Algun
    0.38
    Pl
    0.37
     आर
    0.37
     vec
    0.37
     Enroll
    0.36
     सालों
    0.36
    Activations Density 0.000%

    No Known Activations