© 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. 29501
    Prev
    Next
    INDEX
    Explanations

    code syntax

    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
    שהו
    0.44
    ెక్
    0.40
     obter
    0.39
     ಅಧ್ಯ
    0.38
     특집
    0.38
    
    0.37
     conversaciones
    0.36
     перегово
    0.36
     chamado
    0.36
     города
    0.36
    POSITIVE LOGITS
    <h2>
    0.49
    ada
    0.48
    ue
    0.48
    uk
    0.47
    uer
    0.47
    if
    0.46
    ################
    0.46
    utf
    0.45
    ctu
    0.45
    iat
    0.45
    Activations Density 0.008%

    No Known Activations