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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-16K
    7. 11969
    Prev
    Next
    INDEX
    Explanations

    fill in, fill up, fill me

    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
    ado
    2.38
    ch
    2.34
    ely
    2.27
    ent
    1.94
            
    1.92
                    
    1.88
    <0x80>
    1.88
    ily
    1.87
    are
    1.84
    ig
    1.83
    POSITIVE LOGITS
    اونلو
    2.05
     sweaters
    2.05
     supergiants
    1.98
     catheters
    1.98
     vacancies
    1.95
    できる
    1.94
    ب
    1.92
     billowing
    1.91
    ᡤ
    1.90
    見る
    1.88
    Activations Density 0.132%

    No Known Activations