© 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. 7082
    Prev
    Next
    INDEX
    Explanations

    line or lines

    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
    د
    1.42
    ش
    1.36
    od
    1.28
    ます
    1.18
    म
    1.13
    bboxes
    1.10
    д
    1.06
    ors
    1.05
    BTW
    1.05
    ש
    1.05
    POSITIVE LOGITS
     concentric
    1.13
     불구하고
    1.13
    estion
    1.12
    াত্মক
    1.09
    pecific
    1.07
    াবণ
    1.05
    一场
    1.03
    åt
    1.02
     gerais
    1.02
    та
    1.01
    Activations Density 0.036%

    No Known Activations