© 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. 40-GEMMASCOPE-2-RES-262K
    7. 166434
    Prev
    Next
    INDEX
    Explanations

    sustain, organize, default, minimum

    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_40_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
    池
    0.46
     አካ
    0.44
     池
    0.39
     inferences
    0.37
    एमपी
    0.37
     archives
    0.37
     aiuto
    0.36
    桐
    0.35
    licken
    0.35
     êtes
    0.35
    POSITIVE LOGITS
     Sustain
    0.48
     sustain
    0.45
     organized
    0.44
     Sust
    0.43
    য়াত
    0.42
    бов
    0.41
    Cups
    0.41
     организова
    0.41
    াইভ
    0.40
    рида
    0.39
    Activations Density 0.001%

    No Known Activations