© 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. 154376
    Prev
    Next
    INDEX
    Explanations

    specific words followed by others

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

    pseudo-AI falter restoration deeply

    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
    φάλ
    0.55
    Georges
    0.52
    𝕜
    0.51
     Еўропы
    0.50
    ᕇ
    0.49
    λευτα
    0.49
     kubb
    0.49
    ℚ
    0.49
     مِنْ
    0.49
     États
    0.48
    POSITIVE LOGITS
     S
    0.55
    sie
    0.52
    0.51
     U
    0.50
     weight
    0.47
    '
    0.47
     size
    0.46
    U
    0.44
              
    0.44
     beeindruck
    0.44
    Activations Density 0.000%

    No Known Activations