© 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-262K
    7. 45553
    Prev
    Next
    INDEX
    Explanations

    golden hour lighting

    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
    2.09
    iro
    1.73
     Ancak
    1.67
    ö
    1.66
    ließ
    1.63
    ojo
    1.63
    }))
    1.60
    }));
    1.60
    ió
    1.59
    ic
    1.58
    POSITIVE LOGITS
    ية
    1.75
    ام
    1.73
    ную
    1.66
    انا
    1.58
     prerog
    1.55
     intolerable
    1.48
    сть
    1.44
    て
    1.42
    なぜ
    1.41
    葫
    1.39
    Activations Density 0.009%

    No Known Activations