© 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. 894
    Prev
    Next
    INDEX
    Explanations

    adam, Adam, type, star, alloy

    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
    1.41
    一些
    0.98
     fortifications
    0.96
    </i>
    0.96
     ännu
    0.94
     numero
    0.93
     and
    0.92
    </blockquote>
    0.91
     alcuni
    0.90
    很多的
    0.89
    POSITIVE LOGITS
    v
    1.20
    IK
    1.16
    User
    1.10
    ol
    1.09
    i
    1.09
    ed
    1.05
    y
    1.04
    cí
    1.03
    t
    1.03
    NOT
    1.02
    Activations Density 0.086%

    No Known Activations