© 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. 183509
    Prev
    Next
    INDEX
    Explanations

    residual flavors, required tasks, our staff

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

    burn time, day, northern

    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
    цэ
    0.55
    寳
    0.53
    𝔸
    0.52
    ר
    0.51
    Ά
    0.51
    Dihydro
    0.50
     기능을
    0.49
     клетки
    0.49
     PRICES
    0.49
     பகுதியில்
    0.49
    POSITIVE LOGITS
    s
    0.69
     Northern
    0.52
     northern
    0.52
    context
    0.46
    idents
    0.46
     ence
    0.45
    immune
    0.45
    len
    0.44
    facebook
    0.44
    eventType
    0.44
    Activations Density 0.000%

    No Known Activations