© 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-16K
    7. 10558
    Prev
    Next
    INDEX
    Explanations

    climbing trees

    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_16k_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
    зра
    0.44
    '`--'`--
    0.41
    DisplayName
    0.40
    浠
    0.40
     filoz
    0.39
    熠
    0.39
    ByteBuffer
    0.38
    Converter
    0.38
    洹
    0.37
    Instantiation
    0.37
    POSITIVE LOGITS
     climbing
    2.16
     climb
    1.98
     Climbing
    1.95
     climbed
    1.91
     climbs
    1.88
     Climb
    1.88
     climber
    1.80
     climbers
    1.77
    攀
    1.58
     ladders
    1.52
    Activations Density 0.164%

    No Known Activations