© 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. 1366
    Prev
    Next
    INDEX
    Explanations

    display or displayed

    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
    ע
    1.27
    ます
    1.14
     Ее
    1.14
    okhlov
    1.12
    就这样
    1.09
    ﺘ
    1.09
    ﻤ
    1.07
     unido
    1.02
    t
    1.02
    EE
    1.00
    POSITIVE LOGITS
    potentially
    1.15
     وأن
    1.10
    Shiny
    1.09
    ovne
    1.05
     exibir
    1.04
     brillantes
    1.02
    রূপ
    1.02
    ian
    1.01
    ances
    1.01
     términos
    1.01
    Activations Density 0.373%

    No Known Activations