© 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. 98383
    Prev
    Next
    INDEX
    Explanations

    complimentary things

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

    Shelley portrays

    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
    än
    0.52
     παρου
    0.52
    od
    0.47
    ating
    0.45
    𝐻
    0.44
    ens
    0.43
    als
    0.43
    ade
    0.42
     έγινε
    0.42
    ä
    0.41
    POSITIVE LOGITS
     popol
    0.48
     namens
    0.47
     invern
    0.46
     gratuite
    0.45
     moeder
    0.45
     linguaggio
    0.44
     miễn
    0.44
     popolare
    0.43
     tradisional
    0.43
     attiv
    0.42
    Activations Density 0.000%

    No Known Activations