© 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
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 7865
    Prev
    Next
    INDEX
    Explanations

    coding constructs and library names

    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
    ]
    0.30
     fragmentary
    0.27
     rather
    0.25
     Chief
    0.25
     Hens
    0.25
     patrons
    0.25
     authors
    0.24
     asserted
    0.24
     substantial
    0.24
     Collected
    0.24
    POSITIVE LOGITS
     ujian
    0.32
     residencial
    0.28
     упраж
    0.28
    Airbnb
    0.28
    Ꮡ
    0.28
    銀行
    0.27
     ejercicios
    0.27
    ات
    0.27
    电商
    0.27
     restoran
    0.27
    Activations Density 0.001%

    No Known Activations