© 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. 31-GEMMASCOPE-2-RES-262K
    7. 24873
    Prev
    Next
    INDEX
    Explanations

    listing topics

    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_31_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
    ሜ
    0.50
    дитесь
    0.46
    Incrementor
    0.46
    $.}
    0.45
     അമേരിക്ക
    0.44
    шого
    0.44
    Arquivo
    0.44
    स्तक
    0.43
     olduğuna
    0.43
    者の
    0.43
    POSITIVE LOGITS
    0.53
    ")
    0.46
    ↵
    0.42
    \]
    0.40
     Sugar
    0.40
     video
    0.39
    ')
    0.38
     Pap
    0.38
     Ti
    0.36
     Beta
    0.36
    Activations Density 0.000%

    No Known Activations