© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 9427
    Prev
    Next
    INDEX
    Explanations

    have lucid dreams

    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
    ال
    2.14
     dioxide
    1.34
     sociales
    1.33
    ট
    1.27
    }
    1.27
    }";
    1.25
    ة
    1.24
     रुपए
    1.23
    ’
    1.23
    NETWORK
    1.23
    POSITIVE LOGITS
    y
    1.67
    ledning
    1.51
    ي
    1.50
    лаб
    1.46
    ו
    1.46
    י
    1.45
    йде
    1.40
    嗯
    1.38
    pflicht
    1.34
    𝕤
    1.34
    Activations Density 0.171%

    No Known Activations