© 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. 6619
    Prev
    Next
    INDEX
    Explanations

    JSON code blocks

    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
    ಟ್
    1.38
     phonons
    1.38
     efectiva
    1.36
    })
    1.35
    เพียง
    1.28
     actuaciones
    1.28
    了一个
    1.27
     乀
    1.27
     Campeonato
    1.25
    िसो
    1.23
    POSITIVE LOGITS
    r
    2.80
    ار
    2.17
    i
    2.08
    a
    2.03
    el
    1.98
    an
    1.94
    al
    1.93
    P
    1.90
    on
    1.89
    H
    1.88
    Activations Density 0.276%

    No Known Activations