© 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. 1538
    Prev
    Next
    INDEX
    Explanations

    hiding things

    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
    <0x80>
    1.69
     annealing
    1.34
    ST
    1.29
     conclusions
    1.24
     RO
    1.17
    ltu
    1.17
     coincident
    1.16
     aesthetically
    1.16
    OT
    1.14
    그램
    1.14
    POSITIVE LOGITS
    ról
    1.90
    いた
    1.76
    𝗯
    1.68
     nascost
    1.63
    隠
    1.63
    っいて
    1.54
    ہ
    1.50
     σχετικά
    1.48
    つなが
    1.48
     sesu
    1.47
    Activations Density 0.194%

    No Known Activations