© 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. 45795
    Prev
    Next
    INDEX
    Explanations

    vibration and shaking

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

    vibration or trembling

    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
    pandemic
    0.44
    ocross
    0.44
    Expiry
    0.43
     ਦਿੱ
    0.42
    ยุ
    0.42
     বিগ
    0.42
    ierge
    0.42
    〠
    0.41
    𐰇
    0.41
     ૩
    0.41
    POSITIVE LOGITS
     vibration
    1.26
     vibrations
    1.24
     vibrating
    1.15
     vibrates
    1.15
    振動
    1.13
     vibrate
    1.13
     vibr
    1.10
     Vibration
    1.10
     tremors
    1.02
     Vibr
    0.98
    Activations Density 0.082%

    No Known Activations