© 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. 102587
    Prev
    Next
    INDEX
    Explanations

    streaming content and research

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

    context and moderation

    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
    가를
    0.51
    植
    0.48
    기
    0.46
     verantwortlich
    0.45
    orre
    0.45
    ობს
    0.45
     Steck
    0.44
    Produkt
    0.44
    virk
    0.44
    orra
    0.43
    POSITIVE LOGITS
     হয়ত
    0.47
     tu
    0.46
     แน
    0.45
     interactive
    0.44
     n
    0.44
     extiende
    0.44
     obviously
    0.44
     Volume
    0.44
     opened
    0.43
     Winner
    0.43
    Activations Density 0.001%

    No Known Activations