© 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-262K
    7. 45051
    Prev
    Next
    INDEX
    Explanations

    #include <header.h>

    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
    ли
    1.49
    ла
    1.44
    на
    1.39
    ो
    1.36
    х
    1.30
    га
    1.27
    ния
    1.16
    is
    1.12
    ный
    1.11
    ي
    1.11
    POSITIVE LOGITS
    Thông
    1.23
    Primero
    1.20
    Weiter
    1.19
    Prote
    1.17
    Denne
    1.16
    Purch
    1.11
    Một
    1.10
    Citi
    1.10
     âgé
    1.10
    Ba
    1.09
    Activations Density 0.001%

    No Known Activations