© 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. 179313
    Prev
    Next
    INDEX
    Explanations

    verb followed by noun/preposition

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

    Behaviour, discovery, climbing, images

    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
    কীর
    0.57
    💴
    0.51
    endidikan
    0.47
     مدیر
    0.46
    cInfo
    0.46
    adar
    0.45
    ătoare
    0.45
    ば
    0.45
    ╧
    0.45
    cJ
    0.45
    POSITIVE LOGITS
     peculi
    0.48
    俱
    0.46
     Hopefully
    0.44
     rit
    0.42
     fort
    0.42
     hoff
    0.42
     sabbam
    0.42
     nerv
    0.41
     ভবিষ্যত
    0.41
     couvert
    0.41
    Activations Density 0.001%

    No Known Activations