© 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-3-1B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 5460
    Prev
    Next
    INDEX
    Explanations

    angle or angular measurement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_17_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
     MOV
    0.87
     albumin
    0.85
     POP
    0.82
    chon
    0.81
    MOV
    0.80
    zoa
    0.79
    хло
    0.77
    跳
    0.77
     weight
    0.77
     Pop
    0.76
    POSITIVE LOGITS
     angles
    1.61
     angle
    1.60
     Angle
    1.60
    Angle
    1.53
     Angles
    1.45
    angle
    1.39
    Angles
    1.36
     radians
    1.22
     ángulos
    1.20
     âng
    1.16
    Activations Density 0.202%

    No Known Activations