© 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. 7830
    Prev
    Next
    INDEX
    Explanations

    academic titles and abbreviations

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

    The neuron fires on the (multilingual) preposition “with” (e.g. Greek “με,” Portuguese “com,” Irish “le”).

    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
    ]
    -3.75
    {
    -3.64
    ↵↵
    -3.48
    in
    -3.25
    .
    -3.16
    z
    -2.86
    }
    -2.77
    To
    -2.69
     of
    -2.66
    ].
    -2.66
    POSITIVE LOGITS
     behulp
    3.16
    stood
    3.11
    俛
    3.08
     rése
    2.80
    糴
    2.73
    のデザイン
    2.70
     regard
    2.70
    錞
    2.69
    ዣ
    2.69
    archiwizowane
    2.66
    Activations Density 0.000%

    No Known Activations