© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 28210
    Prev
    Next
    INDEX
    Explanations

    flying and traveling concepts

    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_40_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
    可用
    0.42
     absent
    0.40
     flown
    0.38
    uddho
    0.37
    ố
    0.36
    ্মী
    0.36
     anciens
    0.36
    tní
    0.35
     Extremely
    0.35
     proposition
    0.35
    POSITIVE LOGITS
     saucer
    0.44
    苋
    0.42
    ARGS
    0.39
     Pacheco
    0.39
     Su
    0.38
    arbeiter
    0.38
     pallet
    0.38
     Platforms
    0.38
     Sales
    0.37
    ającym
    0.37
    Activations Density 0.009%

    No Known Activations