© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 45900
    Prev
    Next
    INDEX
    Explanations

    wipes and their uses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ли
    0.72
    ين
    0.68
    ﻨ
    0.65
    l
    0.63
    ne
    0.61
    ңуз
    0.61
    на
    0.59
    Categoria
    0.59
    ري
    0.59
    categoria
    0.58
    POSITIVE LOGITS
     welche
    0.66
     wers
    0.62
    )\
    0.61
     apologizing
    0.61
     objRequest
    0.59
    ,
    0.59
     tors
    0.57
    ).
    0.57
     tenham
    0.57
     defaulting
    0.57
    Activations Density 0.000%

    No Known Activations