© 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. 7676
    Prev
    Next
    INDEX
    Explanations

    ranging from

    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
    𝘿
    1.23
     milik
    1.21
     secondaires
    1.20
    បាន
    1.20
     tiên
    1.20
     ออก
    1.20
    髅
    1.19
     regola
    1.18
     thisTrial
    1.17
    哟
    1.16
    POSITIVE LOGITS
    ০০
    1.66
    ت
    1.66
    al
    1.65
    1
    1.54
    ת
    1.52
    }^{
    1.46
    up
    1.43
    2
    1.42
    א
    1.42
    5
    1.41
    Activations Density 0.025%

    No Known Activations