© 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. 69685
    Prev
    Next
    INDEX
    Explanations

    travel destinations and requirements

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

    shipped long distances

    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
    носи
    0.44
    🏞
    0.43
     Existing
    0.43
    মূল
    0.42
    unused
    0.42
    🌈
    0.42
    ඒ
    0.42
     Shouldn
    0.40
    Okay
    0.40
    𝙰
    0.40
    POSITIVE LOGITS
     lapar
    0.52
     trocar
    0.48
     quartos
    0.46
     histological
    0.45
     Drosophila
    0.45
     histology
    0.45
     surgeon
    0.45
     surgeons
    0.44
     dogged
    0.44
     endonuclease
    0.44
    Activations Density 0.001%

    No Known Activations