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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 196714
    Prev
    Next
    INDEX
    Explanations

    natural language units like paragraphs or numbers

    np_acts-logits-general · gemini-2.5-flash-lite

    introduces a description or breakdown

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    эм
    0.55
    誂
    0.49
     делается
    0.48
    cerning
    0.48
     なん
    0.47
     తే
    0.47
    комо
    0.47
    edinte
    0.47
     ரசிக
    0.47
     महे
    0.47
    POSITIVE LOGITS
    ن
    0.46
    Fragment
    0.45
     وهكذا
    0.43
     episodes
    0.42
    Again
    0.41
    ق
    0.41
    نا
    0.41
    Previously
    0.41
     ธ
    0.41
     fragments
    0.40
    Activations Density 0.001%

    No Known Activations