© 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. 238386
    Prev
    Next
    INDEX
    Explanations

    ball joint

    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
    ع
    0.49
    grave
    0.44
    grove
    0.44
    clinic
    0.42
    bh
    0.41
     tanpa
    0.41
    crypt
    0.41
    ELIG
    0.41
    Leary
    0.40
    elig
    0.40
    POSITIVE LOGITS
    стрее
    0.52
    韶
    0.50
    পতি
    0.48
    য়াস
    0.47
     φω
    0.46
     mandib
    0.46
     stroj
    0.46
    ტის
    0.45
     politici
    0.45
    უქ
    0.45
    Activations Density 0.000%

    No Known Activations