© 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. 93568
    Prev
    Next
    INDEX
    Explanations

    technical terms and specific entities

    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
    Safety
    0.47
     αυτές
    0.44
     установ
    0.39
     ভূমিকম্প
    0.39
     αυτά
    0.39
     αυτή
    0.38
    ᱦ
    0.38
    ней
    0.38
    ıştır
    0.38
    ິນ
    0.37
    POSITIVE LOGITS
    ])).
    0.46
    🐞
    0.43
    renzia
    0.41
     BETTER
    0.41
    viar
    0.40
    랄
    0.40
    해야
    0.39
     이후
    0.39
    מבר
    0.39
     decisions
    0.39
    Activations Density 0.010%

    No Known Activations