© 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. 20161
    Prev
    Next
    INDEX
    Explanations

    code and text formatting

    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
     Natürlich
    0.42
     circumstantial
    0.41
     Anforderungen
    0.41
     Systeme
    0.41
     retShape
    0.40
     laboratorium
    0.40
     "¿
    0.40
    🏕
    0.40
     LaTeX
    0.40
     ضمن
    0.39
    POSITIVE LOGITS
     בשנת
    0.37
     beautiful
    0.37
    ilish
    0.31
     wundersch
    0.30
     краси
    0.30
    tim
    0.30
    h
    0.30
    beautiful
    0.29
    pretrained
    0.29
     হেন
    0.29
    Activations Density 0.270%

    No Known Activations