© 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. 18657
    Prev
    Next
    INDEX
    Explanations

    outdoor adventure and hiking

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

    hiking and outdoor adventures

    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
    苺
    0.59
    indentLevel
    0.56
    餑
    0.55
    砂糖
    0.54
     stateMutability
    0.54
     graphon
    0.54
    ᡤ
    0.54
     ガラス
    0.53
    錠
    0.52
    齙
    0.52
    POSITIVE LOGITS
     backcountry
    1.38
     Hiking
    1.34
     hiking
    1.31
     hikers
    1.28
    Hiking
    1.27
     mountaine
    1.23
     hiker
    1.22
     backpacking
    1.17
     kayaking
    1.13
    hiking
    1.13
    Activations Density 0.250%

    No Known Activations