© 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. 45521
    Prev
    Next
    INDEX
    Explanations

    location marker

    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
    datei
    1.30
    ست
    1.26
    0
    1.17
    ار
    1.16
    atud
    1.16
    de
    1.14
     itu
    1.13
    o
    1.09
    δες
    1.08
    ը
    1.07
    POSITIVE LOGITS
     formerly
    1.09
     outskirts
    1.02
    }
    1.01
     valuables
    0.98
    <bos>
    0.96
     strolled
    0.93
     praised
    0.93
     elucidate
    0.93
     equator
    0.93
    녠
    0.92
    Activations Density 0.016%

    No Known Activations