© 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. 86088
    Prev
    Next
    INDEX
    Explanations

    specific word contexts

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

    checkpointing

    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
     कैटेगरी
    0.46
    ในช่วง
    0.46
    如果
    0.46
    น
    0.45
     বিরাট
    0.44
    มีการ
    0.44
     বাড়ির
    0.44
    انون
    0.44
    榃
    0.43
    奥
    0.43
    POSITIVE LOGITS
     жид
    0.43
     chaleur
    0.43
     vidas
    0.42
     deseas
    0.42
     drunkenness
    0.42
     жиз
    0.41
     grasped
    0.40
     misfortunes
    0.40
     adot
    0.40
     belonged
    0.40
    Activations Density 0.000%

    No Known Activations