© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-4B-IT
    3. 9-GEMMASCOPE-2-RES-16K
    4. 622
    Prev
    Next
    INDEX
    Explanations

    state of action or being

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_9_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
    ت
    1.07
    ҙ
    1.04
    дые
    1.02
    gameObjects
    1.00
    ូ
    1.00
     encased
    0.99
     fruition
    0.95
    gameState
    0.95
     inductively
    0.94
    *}$
    0.92
    POSITIVE LOGITS
     peut
    1.16
     puede
    1.05
     mayoría
    1.02
    おそらく
    1.01
     것을
    1.01
     может
    0.99
    at
    0.98
    ihal
    0.97
    \]
    0.93
    nese
    0.91
    Activations Density 0.000%

    No Known Activations