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

    Neuronpedia

    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. 30439
    Prev
    Next
    INDEX
    Explanations

    illegal or dangerous activities

    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
    INK
    0.48
     PFAS
    0.46
     FAST
    0.45
    在
    0.43
     when
    0.42
     Callable
    0.42
    ]
    0.41
     LIN
    0.41
     QUICK
    0.40
     coales
    0.39
    POSITIVE LOGITS
     yalnız
    0.54
     především
    0.47
     bakter
    0.44
    جهات
    0.44
     eben
    0.44
     atlet
    0.44
     appunto
    0.44
     informacion
    0.44
    شي
    0.43
    ර
    0.43
    Activations Density 0.001%

    No Known Activations