© 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. 9213
    Prev
    Next
    INDEX
    Explanations

    crane or Croatia

    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
    𝙨
    1.48
    s
    1.47
    ો
    1.46
    sensors
    1.43
    تها
    1.40
    ilibrium
    1.39
    ックス
    1.36
     respectiv
    1.36
    sü
    1.35
    ू
    1.35
    POSITIVE LOGITS
    ق
    1.55
    に必要な
    1.48
    мо
    1.47
    дно
    1.45
    া
    1.45
     particulières
    1.41
    ﻜ
    1.41
    ين
    1.38
    ться
    1.34
    Գ
    1.32
    Activations Density 0.026%

    No Known Activations