© 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. 16-GEMMASCOPE-2-RES-262K
    4. 28401
    Prev
    Next
    INDEX
    Explanations

    podcast episodes and descriptions

    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_16_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
     insuficiente
    0.57
    ικής
    0.56
     ojos
    0.53
    ινή
    0.53
     пище
    0.52
     recharging
    0.52
    စား
    0.51
    餐
    0.51
     Oscars
    0.51
     食品
    0.51
    POSITIVE LOGITS
     podcast
    1.06
    Podcast
    0.99
     Podcast
    0.95
     podcasts
    0.91
    podcast
    0.88
     Podcasts
    0.75
    radio
    0.73
    Radio
    0.70
    🎧
    0.68
     radio
    0.66
    Activations Density 0.012%

    No Known Activations