© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 11258
    Prev
    Next
    INDEX
    Explanations

    land and related concepts

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

    This neuron selectively activates on occurrences of the word “land” (in any casing).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     कक्ष
    0.61
     respondents
    0.57
    iter
    0.57
    ને
    0.56
     rooms
    0.55
    otional
    0.54
     Respondents
    0.53
     \
    0.52
    abola
    0.51
     கொள்ளுங்கள்
    0.50
    POSITIVE LOGITS
     Land
    0.99
    Land
    0.97
     LAND
    0.92
     land
    0.92
    陸
    0.84
     लैंड
    0.83
    SCAPE
    0.77
    lord
    0.75
    lady
    0.75
    LORD
    0.73
    Activations Density 0.111%

    No Known Activations