© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-16K
    7. 3644
    Prev
    Next
    INDEX
    Explanations

    specific contexts after common tokens

    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_16k_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
    ت
    1.38
    ik
    1.30
    im
    1.29
    また
    1.21
    an
    1.17
    ura
    1.16
     alcuna
    1.13
    re
    1.09
    ли
    1.09
    duh
    1.09
    POSITIVE LOGITS
    녘
    0.90
     paradigm
    0.84
    ైన
    0.84
     prosperous
    0.84
     carefree
    0.84
     exit
    0.82
     licensure
    0.82
     scramble
    0.82
     ممکن
    0.82
     witches
    0.81
    Activations Density 0.001%

    No Known Activations