© 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. 22423
    Prev
    Next
    INDEX
    Explanations

    NOW, THEREFORE

    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
     violates
    0.46
     breaches
    0.39
     firewall
    0.38
     Kopf
    0.38
     VCO
    0.38
     লঙ্ঘন
    0.37
    代わりに
    0.36
    ():
    0.36
     bottoms
    0.36
    verses
    0.36
    POSITIVE LOGITS
     ಜೀವನ
    0.41
    Singh
    0.41
     Unwin
    0.41
    च्छ
    0.41
    inisc
    0.41
    adería
    0.40
    Evan
    0.40
    ચ્છ
    0.40
    ystycz
    0.40
    LOGGER
    0.40
    Activations Density 0.001%

    No Known Activations