© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 170300
    Prev
    Next
    INDEX
    Explanations

    you're reaching out / asking

    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
    "$
    0.51
     цены
    0.46
    "+
    0.46
     nu
    0.45
     fiyat
    0.45
    "",
    0.44
     skutecz
    0.44
     uzun
    0.44
     navegador
    0.44
    ".$
    0.43
    POSITIVE LOGITS
    created
    0.54
    破壊
    0.45
    ೇಯ
    0.45
    creating
    0.45
    sealed
    0.44
    小屋
    0.44
    principles
    0.44
    Fourier
    0.44
     superposition
    0.43
    organisms
    0.43
    Activations Density 0.003%

    No Known Activations