© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-16K
    7. 7484
    Prev
    Next
    INDEX
    Explanations

    abstract : ** Abstract ** Thinking

    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_16k_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
    i
    2.20
    ioc
    2.09
    ну
    2.00
    ر
    1.94
    oing
    1.90
    deserved
    1.86
    ्ञ
    1.82
    wdriver
    1.75
    يًا
    1.75
    يء
    1.74
    POSITIVE LOGITS
    speople
    2.05
     volna
    1.94
    ively
    1.82
    ᆹ
    1.79
    $
    1.78
     filaments
    1.74
     restrain
    1.71
     devour
    1.66
     diminish
    1.66
    }$
    1.65
    Activations Density 0.070%

    No Known Activations