© 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-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 9576
    Prev
    Next
    INDEX
    Explanations

    citation references

    np_acts-logits-general · gemini-2.5-flash-lite

    code structure and connection

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_40_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     DENUMIRE
    0.44
    }{{
    0.42
    ставить
    0.41
     তাছাড়া
    0.41
     знаходи
    0.41
     Respuesta
    0.41
     மேற்பட்ட
    0.41
     Зна
    0.40
     Membuat
    0.40
    ঙ্কের
    0.40
    POSITIVE LOGITS
     Brav
    0.42
    Honor
    0.38
    ᷅
    0.38
     rồi
    0.38
     Sonic
    0.37
    FU
    0.37
     FU
    0.37
     overall
    0.36
     pad
    0.36
     Honor
    0.36
    Activations Density 0.004%

    No Known Activations