© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 76548
    Prev
    Next
    INDEX
    Explanations

    intended to

    np_acts-logits-general · gemini-2.5-flash-lite

    ato pattern

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
     estudiar
    0.50
    תר
    0.49
    持续
    0.49
     И
    0.48
    קי
    0.48
    小子
    0.48
    嘿
    0.48
    反复
    0.47
    ис
    0.46
     obviamente
    0.45
    POSITIVE LOGITS
    ado
    0.58
    adu
    0.57
    atos
    0.54
    aked
    0.50
    atto
    0.46
    ಲಾಯಿತು
    0.46
    aky
    0.46
    ande
    0.46
    akes
    0.46
     لکھنے
    0.46
    Activations Density 0.000%

    No Known Activations