© 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. 8440
    Prev
    Next
    INDEX
    Explanations

    mindset or mentality

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

    The neuron specifically activates on the word “mindset” (and closely related tokens), flagging occurrences of that term.

    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
     with
    -2.20
     Despite
    -2.20
    }:
    -2.19
     persiapan
    -2.17
     Shortly
    -2.11
    }
    -2.11
    }-\
    -2.09
     Schülern
    -2.06
    我一直
    -2.06
     Whether
    -2.06
    POSITIVE LOGITS
    是非常
    2.89
    But
    2.56
    是用
    2.28
    犒
    2.13
     وآ
    2.13
    No
    2.09
    complexContent
    2.09
    ſu
    2.00
    We
    1.99
    they
    1.99
    Activations Density 0.001%

    No Known Activations