© 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-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 7527
    Prev
    Next
    INDEX
    Explanations

    python input()

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_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
    +}\
    1.25
     spiced
    1.23
     embossed
    1.22
    ang
    1.16
     Sachin
    1.13
    etern
    1.13
    et
    1.11
    >`;
    1.10
     hashlib
    1.10
     networked
    1.09
    POSITIVE LOGITS
    ة
    1.55
    ải
    0.93
    ünst
    0.92
    ส
    0.90
    Have
    0.89
    ﻲ
    0.89
    Hö
    0.88
     ответить
    0.88
    如果
    0.86
    ùng
    0.85
    Activations Density 0.016%

    No Known Activations