© 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. 62235
    Prev
    Next
    INDEX
    Explanations

    high [noun]

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

    high school, high level, high knees

    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
     Armee
    0.65
     Osmanlı
    0.63
    િ
    0.61
     powied
    0.61
     awning
    0.59
     ağırl
    0.59
     QnrB
    0.59
    ೋಜನ
    0.59
    য়
    0.59
     utterly
    0.58
    POSITIVE LOGITS
    high
    1.26
    High
    1.16
     high
    1.16
     High
    1.10
    高
    1.05
     высоко
    1.02
    HIGH
    0.98
     हाई
    0.93
    的高
    0.91
     HIGH
    0.90
    Activations Density 0.103%

    No Known Activations