© 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. 8384
    Prev
    Next
    INDEX
    Explanations

    ton of

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

    The neuron consistently activates on the token “ton” (as in “a ton of …”), i.e. occurrences of “ton” indicating “a lot of.”

    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
    The
    -2.48
    哢
    -2.16
    at
    -2.13
    ????????
    -2.11
    b
    -2.09
    殽
    -2.09
    on
    -2.02
    what
    -2.00
    ??????
    -1.95
    while
    -1.93
    POSITIVE LOGITS
    ],
    2.38
    ,"
    2.38
    },
    2.33
    𓇼
    2.28
    溷
    2.23
    ،
    2.13
    übung
    2.06
    ."
    2.06
     (>
    2.05
    );
    2.03
    Activations Density 0.002%

    No Known Activations