© 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. 43668
    Prev
    Next
    INDEX
    Explanations

    minimum qualifications

    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
    ول
    1.96
    ेक्स
    1.76
    नगर
    1.72
    گزاری
    1.72
     mignon
    1.71
    К
    1.70
    ᱽ
    1.67
    ीण
    1.66
     emergencies
    1.66
    ことにより
    1.66
    POSITIVE LOGITS
    rs
    2.02
    cs
    1.91
    ms
    1.88
    co
    1.84
    ae
    1.80
    sk
    1.73
    s
    1.73
    rd
    1.72
    ς
    1.71
    vai
    1.63
    Activations Density 0.004%

    No Known Activations