© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 19512
    Prev
    Next
    INDEX
    Explanations

    off the coast

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

    This neuron detects geographic location phrases, particularly “off the [coast/region] of …” constructions identifying where something is found.

    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
     contacter
    -1.44
     calore
    -1.33
     vidi
    -1.26
    wigs
    -1.23
    aiso
    -1.23
    vyš
    -1.22
     spu
    -1.20
     dévelo
    -1.20
     mitos
    -1.20
     Vz
    -1.19
    POSITIVE LOGITS
     I
    1.45
     from
    1.40
     In
    1.23
     f
    1.22
     i
    1.21
     -
    1.16
    },
    1.13
     This
    1.13
     b
    1.13
     sija
    1.12
    Activations Density 0.052%

    No Known Activations