© 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
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-262K
    4. 30860
    Prev
    Next
    INDEX
    Explanations

    popcorn

    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
    Z
    1.50
     numéro
    1.48
     rio
    1.44
     nouvel
    1.44
    퐶
    1.44
    CH
    1.41
    К
    1.41
     pericolo
    1.39
     antérieure
    1.37
     aérea
    1.34
    POSITIVE LOGITS
    م
    2.06
    مون
    1.88
    m
    1.70
    ات
    1.63
    ين
    1.57
    <0x80>
    1.47
    ام
    1.47
     refills
    1.45
    ع
    1.45
    াম
    1.41
    Activations Density 0.001%

    No Known Activations