© 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. 111961
    Prev
    Next
    INDEX
    Explanations

    said to, wait to, lengthy absence

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

    directly employing

    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
    骸
    0.51
    㳚
    0.49
     eventos
    0.46
    عار
    0.46
    อก
    0.46
     penurunan
    0.46
    프트
    0.45
     distortions
    0.45
    Всім
    0.44
    欝
    0.44
    POSITIVE LOGITS
     تدخل
    0.46
     얼마
    0.45
    nas
    0.43
    sberg
    0.42
     bedrij
    0.41
    ListOf
    0.40
    ================
    0.40
     পরিচয়
    0.40
    anchen
    0.40
     फीड
    0.39
    Activations Density 0.000%

    No Known Activations