© 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. 252541
    Prev
    Next
    INDEX
    Explanations

    news time, resulted in, impact emigration

    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
    虽然
    0.49
    Съ
    0.48
    리와
    0.48
    Фі
    0.47
     누가
    0.47
    櫒
    0.47
    날
    0.46
    윰
    0.46
    虽
    0.45
     pénétr
    0.45
    POSITIVE LOGITS
     hopping
    0.48
     kilometres
    0.47
     caras
    0.47
     cientos
    0.45
     oversees
    0.44
     eels
    0.44
     alerted
    0.44
     beliefs
    0.43
     বন্দ
    0.43
     earmarked
    0.43
    Activations Density 0.000%

    No Known Activations