© 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. 8307
    Prev
    Next
    INDEX
    Explanations

    in which

    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
    ות
    2.17
    ed
    1.66
    ў
    1.56
    ান্তরিত
    1.52
     indications
    1.49
     invigor
    1.45
    ী
    1.37
    quark
    1.34
    highway
    1.34
    et
    1.33
    POSITIVE LOGITS
    soever
    2.34
     związ
    2.16
    ü
    2.16
    ת
    2.13
    ă
    2.11
    𝚜
    2.08
     amplo
    1.99
     భాగంగా
    1.97
    客様
    1.93
    ı
    1.88
    Activations Density 0.011%

    No Known Activations