© 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. 22653
    Prev
    Next
    INDEX
    Explanations

    jungle swinging

    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
    郗
    0.42
    glacial
    0.41
    })^
    0.41
     dilat
    0.40
    뜹
    0.39
    dilation
    0.38
     Correctional
    0.38
    PDO
    0.38
    뻐
    0.38
    GV
    0.38
    POSITIVE LOGITS
     jungle
    1.07
     Jungle
    1.02
     Tar
    0.93
    Tar
    0.84
     jungles
    0.81
     swinging
    0.78
     tar
    0.74
     Swinging
    0.72
     swung
    0.66
     swing
    0.65
    Activations Density 0.005%

    No Known Activations