Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-262K
    4. 461
    Prev
    Next
    INDEX
    Explanations

    John followed by a name

    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
    د
    2.41
    dır
    2.31
    uction
    2.28
    ut
    2.17
    ires
    2.16
    us
    2.06
     ώστε
    2.06
    т
    2.06
    ש
    1.98
    lı
    1.85
    POSITIVE LOGITS
     fief
    1.98
    ों
    1.97
     Cena
    1.93
    athan
    1.92
     Objet
    1.91
     verificar
    1.89
    ห์
    1.86
     Deere
    1.86
    ﻅ
    1.84
    鸪
    1.84
    Activations Density 0.002%

    No Known Activations