© 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. 70018
    Prev
    Next
    INDEX
    Explanations

    offers and public service announcements

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

    cloud computing, garage startup

    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
     submits
    0.45
     losing
    0.44
     submitting
    0.44
     decreases
    0.42
     pierde
    0.41
     每
    0.41
    aniyam
    0.41
     killed
    0.40
     বণ্ট
    0.40
     decreasing
    0.40
    POSITIVE LOGITS
    discuss
    0.41
     nonché
    0.41
     terbaru
    0.38
    证实
    0.38
     modernist
    0.37
     concep
    0.36
     discuss
    0.36
    沏
    0.36
     nonchal
    0.35
    謦
    0.35
    Activations Density 0.003%

    No Known Activations