© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 3002
    Prev
    Next
    INDEX
    Explanations

    irrational

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     static
    0.44
     error
    0.42
     junto
    0.42
     elapsed
    0.42
     contain
    0.41
     obtain
    0.40
    :
    0.40
     contains
    0.40
     contienen
    0.40
     mediante
    0.39
    POSITIVE LOGITS
    Spending
    0.46
    這
    0.45
    Marketing
    0.44
    这家
    0.44
    Diploma
    0.44
    这些人
    0.44
    Prosec
    0.44
    這個
    0.43
    ऐसा
    0.43
    這麼
    0.43
    Activations Density 0.000%

    No Known Activations