© 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. 159030
    Prev
    Next
    INDEX
    Explanations

    Samsung Galaxy

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

    phrases like growing awareness, relying on

    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
     Kxh
    0.51
     liberdade
    0.47
     एक्सरसा
    0.47
    %}
    0.47
     ಮೆ
    0.46
     মি
    0.46
     língua
    0.45
     setembro
    0.44
     azide
    0.44
     dinheiro
    0.44
    POSITIVE LOGITS
    2
    0.52
    АН
    0.52
    IDO
    0.52
    OD
    0.49
    数
    0.49
    Ubuntu
    0.48
    ANE
    0.47
    Orange
    0.47
    ด
    0.47
    世界
    0.47
    Activations Density 0.000%

    No Known Activations