© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 39059
    Prev
    Next
    INDEX
    Explanations

    from the ground up

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

    The neuron activates strongly on instances of “ground” and “up,” effectively detecting the phrase “from the ground up.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     jsonObj
    -1.44
    洶
    -1.40
    ???:
    -1.37
    детская
    -1.36
    ⚘
    -1.34
     in
    -1.31
    ンテナ
    -1.30
    белый
    -1.30
    ⩤
    -1.28
    tification
    -1.26
    POSITIVE LOGITS
     */
    1.60
     
    1.59
    man
    1.57
    —
    1.54
    )
    1.53
     }^{
    1.52
    他
    1.51
     />
    1.45
     s
    1.43
     U
    1.38
    Activations Density 0.012%

    No Known Activations